=== This is the CP2K Performance-Test ===


Already up to date.
Current branch master is up to date.


Already up to date.
Current branch master is up to date.

 GIT Revision: 0f4c3be663d366d31f5e87b3e15a929b1755fd76


################# ARCHITECTURE FILE ##################
#!/bin/bash
#
# CP2K arch file for Cray-XC50 (Piz Daint, CSCS, GPU partition)
#
# Tested with: GNU 9.3.0, Cray-MPICH 7.7.18, Cray-libsci 20.09.1, Cray-FFTW 3.3.8.10,
#              COSMA 2.6.2, ELPA 2022.11.001.rc2, LIBINT 2.6.0, LIBPEXSI 1.2.0,
#              LIBXC 6.0.0, LIBVORI 220621, LIBXSMM 1.17, PLUMED 2.8.0,
#              SIRIUS 7.3.2, SPGLIB 1.16.2
#
# Usage: Source this arch file and then run make as instructed.
#        A full toolchain installation is performed as default.
#        Replace or adapt the "module add" commands below if needed.
#
# Author: Matthias Krack (15.12.2022)
#
# \
   if [ "${0}" = "${BASH_SOURCE}" ]; then \
      echo "ERROR: Script ${0##*/} must be sourced"; \
      echo "Usage: source ${0##*/}"; \
      exit 1; \
   fi; \
   this_file=${BASH_SOURCE##*/}; \
   if [ -n "${1}" ]; then \
      gcc_version="${1}"; \
   else \
      gcc_version="9.3.0"; \
   fi; \
   module add daint-gpu; \
   module rm PrgEnv-cray; \
   module add PrgEnv-gnu; \
   module rm gcc; \
   module add gcc/${gcc_version}; \
   module add cray-fftw/3.3.8.10; \
   module add cudatoolkit; \
   echo "Expected setup:"; \
   echo "   cray-mpich/7.7.18"; \
   echo "   craype-haswell"; \
   echo "   daint-gpu/21.09"; \
   echo "   craype/2.7.10"; \
   echo "   cray-libsci/20.09.1"; \
   echo "   PrgEnv-gnu/6.0.10"; \
   echo "   gcc/${gcc_version}"; \
   echo "   cray-fftw/3.3.8.10"; \
   echo "   cudatoolkit/11.0.2_3.38-8.1__g5b73779"; \
   module list; \
   module -f save cp2k_gpu_gnu_psmp; \
   echo "To load the required modules in your batch job script, use:"; \
   echo "   module restore cp2k_gpu_gnu_psmp"; \
   cd tools/toolchain; \
   ./install_cp2k_toolchain.sh --enable-cuda=yes --gpu-ver=P100 -j${maxtasks} --no-arch-files --with-gcc=system --with-libvdwxc --with-pexsi --with-plumed; \
   cd ../..; \
   printf "Sourcing ${PWD}/tools/toolchain/install/setup ... "; \
   source ${PWD}/tools/toolchain/install/setup; \
   printf "done\n"; \
   echo "Check the output above for error messages and consistency!"; \
   echo "If everything is OK, you can build a CP2K production binary with"; \
   echo "   make -j ARCH=${this_file%.*} VERSION=${this_file##*.}"; \
   echo "Alternatively, you can add further checks, e.g. for regression testing, with"; \
   echo "   make -j ARCH=${this_file%.*} VERSION=${this_file##*.} DO_CHECKS=yes"; \
   echo "or build CP2K as a library with"; \
   echo "   make -j ARCH=${this_file%.*} VERSION=${this_file##*.} libcp2k"; \
   return

# Set options
DO_CHECKS      := no
USE_ACC        := yes
USE_COSMA      := 2.6.2
USE_ELPA       := 2022.11.001.rc2
USE_LIBINT     := 2.6.0
USE_LIBPEXSI   := 1.2.0
USE_LIBVORI    := 220621
USE_LIBXC      := 6.0.0
USE_LIBXSMM    := 1.17
USE_PLUMED     := 2.8.0
#USE_QUIP       := 0.9.10
USE_SIRIUS     := 7.3.2
USE_SPGLIB     := 1.16.2
# Only needed for SIRIUS
LIBVDWXC_VER   := 0.4.0
SPFFT_VER      := 1.0.6
SPLA_VER       := 1.5.4
HDF5_VER       := 1.12.0
# Only needed for LIBPEXSI
SCOTCH_VER     := 6.0.0
SUPERLU_VER    := 6.1.0

LMAX           := 5
MAX_CONTR      := 4

GPUVER         := P100
OFFLOAD_TARGET := cuda

CC             := cc
CXX            := CC
OFFLOAD_CC     := nvcc
FC             := ftn
LD             := ftn
AR             := ar -r

# cc, CC, and ftn include already the proper -march flag
CFLAGS         := -O2 -fopenmp -fopenmp-simd -ftree-vectorize -funroll-loops -g

DFLAGS         := -D__parallel
DFLAGS         += -D__SCALAPACK
DFLAGS         += -D__FFTW3
DFLAGS         += -D__MAX_CONTR=$(strip $(MAX_CONTR))

INSTALL_PATH   := $(PWD)/tools/toolchain/install

ifeq ($(DO_CHECKS), yes)
   DFLAGS         += -D__CHECK_DIAG
endif

ifeq ($(USE_ACC), yes)
   DFLAGS         += -D__DBCSR_ACC
   DFLAGS         += -D__OFFLOAD_CUDA
# Possibly no performance gain with PW_CUDA currently
   DFLAGS         += -D__NO_OFFLOAD_PW
endif

ifneq ($(USE_PLUMED),)
   USE_PLUMED     := $(strip $(USE_PLUMED))
   PLUMED_LIB     := $(INSTALL_PATH)/plumed-$(USE_PLUMED)/lib
   DFLAGS         += -D__PLUMED2
   USE_GSL        := 2.7
   LIBS           += $(PLUMED_LIB)/libplumed.a
endif

ifneq ($(USE_ELPA),)
   USE_ELPA       := $(strip $(USE_ELPA))
   TARGET         := nvidia
   ELPA_INC       := $(INSTALL_PATH)/elpa-$(USE_ELPA)/$(TARGET)/include/elpa-$(USE_ELPA)
   ELPA_LIB       := $(INSTALL_PATH)/elpa-$(USE_ELPA)/$(TARGET)/lib
   CFLAGS         += -I$(ELPA_INC)/elpa -I$(ELPA_INC)/modules
   DFLAGS         += -D__ELPA
   ifeq ($(TARGET), nvidia)
      DFLAGS         += -D__ELPA_NVIDIA_GPU
   endif
   LIBS           += $(ELPA_LIB)/libelpa.a
endif

ifneq ($(USE_QUIP),)
   USE_QUIP       := $(strip $(USE_QUIP))
   QUIP_INC       := $(INSTALL_PATH)/quip-$(USE_QUIP)/include
   QUIP_LIB       := $(INSTALL_PATH)/quip-$(USE_QUIP)/lib
   CFLAGS         += -I$(QUIP_INC)
   DFLAGS         += -D__QUIP
   LIBS           += $(QUIP_LIB)/libquip_core.a
   LIBS           += $(QUIP_LIB)/libatoms.a
   LIBS           += $(QUIP_LIB)/libFoX_sax.a
   LIBS           += $(QUIP_LIB)/libFoX_common.a
   LIBS           += $(QUIP_LIB)/libFoX_utils.a
   LIBS           += $(QUIP_LIB)/libFoX_fsys.a
endif

ifneq ($(USE_LIBPEXSI),)
   USE_LIBPEXSI   := $(strip $(USE_LIBPEXSI))
   SCOTCH_VER     := $(strip $(SCOTCH_VER))
   SUPERLU_VER    := $(strip $(SUPERLU_VER))
   LIBPEXSI_INC   := $(INSTALL_PATH)/pexsi-$(USE_LIBPEXSI)/include
   LIBPEXSI_LIB   := $(INSTALL_PATH)/pexsi-$(USE_LIBPEXSI)/lib
   SCOTCH_INC     := $(INSTALL_PATH)/scotch-$(SCOTCH_VER)/include
   SCOTCH_LIB     := $(INSTALL_PATH)/scotch-$(SCOTCH_VER)/lib
   SUPERLU_INC    := $(INSTALL_PATH)/superlu_dist-$(SUPERLU_VER)/include
   SUPERLU_LIB    := $(INSTALL_PATH)/superlu_dist-$(SUPERLU_VER)/lib
   CFLAGS         += -I$(LIBPEXSI_INC) -I$(SCOTCH_INC) -I$(SUPERLU_INC)
   DFLAGS         += -D__LIBPEXSI
   LIBS           += $(LIBPEXSI_LIB)/libpexsi.a
   LIBS           += $(SUPERLU_LIB)/libsuperlu_dist.a
   LIBS           += $(SCOTCH_LIB)/libptscotchparmetis.a
   LIBS           += $(SCOTCH_LIB)/libptscotch.a
   LIBS           += $(SCOTCH_LIB)/libptscotcherr.a
   LIBS           += $(SCOTCH_LIB)/libscotchmetis.a
   LIBS           += $(SCOTCH_LIB)/libscotch.a
endif

ifneq ($(USE_LIBVORI),)
   USE_LIBVORI    := $(strip $(USE_LIBVORI))
   LIBVORI_LIB    := $(INSTALL_PATH)/libvori-$(USE_LIBVORI)/lib
   DFLAGS         += -D__LIBVORI
   LIBS           += $(LIBVORI_LIB)/libvori.a
endif

ifneq ($(USE_LIBXC),)
   USE_LIBXC      := $(strip $(USE_LIBXC))
   LIBXC_INC      := $(INSTALL_PATH)/libxc-$(USE_LIBXC)/include
   LIBXC_LIB      := $(INSTALL_PATH)/libxc-$(USE_LIBXC)/lib
   CFLAGS         += -I$(LIBXC_INC)
   DFLAGS         += -D__LIBXC
   LIBS           += $(LIBXC_LIB)/libxcf03.a
   LIBS           += $(LIBXC_LIB)/libxc.a
endif

ifneq ($(USE_LIBINT),)
   USE_LIBINT     := $(strip $(USE_LIBINT))
   LMAX           := $(strip $(LMAX))
   LIBINT_INC     := $(INSTALL_PATH)/libint-v$(USE_LIBINT)-cp2k-lmax-$(LMAX)/include
   LIBINT_LIB     := $(INSTALL_PATH)/libint-v$(USE_LIBINT)-cp2k-lmax-$(LMAX)/lib
   CFLAGS         += -I$(LIBINT_INC)
   DFLAGS         += -D__LIBINT
   LIBS           += $(LIBINT_LIB)/libint2.a
endif

ifneq ($(USE_SPGLIB),)
   USE_SPGLIB     := $(strip $(USE_SPGLIB))
   SPGLIB_INC     := $(INSTALL_PATH)/spglib-$(USE_SPGLIB)/include
   SPGLIB_LIB     := $(INSTALL_PATH)/spglib-$(USE_SPGLIB)/lib
   CFLAGS         += -I$(SPGLIB_INC)
   DFLAGS         += -D__SPGLIB
   LIBS           += $(SPGLIB_LIB)/libsymspg.a
endif

ifneq ($(USE_LIBXSMM),)
   USE_LIBXSMM    := $(strip $(USE_LIBXSMM))
   LIBXSMM_INC    := $(INSTALL_PATH)/libxsmm-$(USE_LIBXSMM)/include
   LIBXSMM_LIB    := $(INSTALL_PATH)/libxsmm-$(USE_LIBXSMM)/lib
   CFLAGS         += -I$(LIBXSMM_INC)
   DFLAGS         += -D__LIBXSMM
   LIBS           += $(LIBXSMM_LIB)/libxsmmf.a
   LIBS           += $(LIBXSMM_LIB)/libxsmm.a
endif

ifneq ($(USE_SIRIUS),)
   USE_SIRIUS     := $(strip $(USE_SIRIUS))
   HDF5_VER       := $(strip $(HDF5_VER))
   HDF5_LIB       := $(INSTALL_PATH)/hdf5-$(HDF5_VER)/lib
   LIBVDWXC_VER   := $(strip $(LIBVDWXC_VER))
   LIBVDWXC_INC   := $(INSTALL_PATH)/libvdwxc-$(LIBVDWXC_VER)/include
   LIBVDWXC_LIB   := $(INSTALL_PATH)/libvdwxc-$(LIBVDWXC_VER)/lib
   SPFFT_VER      := $(strip $(SPFFT_VER))
   SPFFT_INC      := $(INSTALL_PATH)/SpFFT-$(SPFFT_VER)/include
   SPLA_VER       := $(strip $(SPLA_VER))
   SPLA_INC       := $(INSTALL_PATH)/SpLA-$(SPLA_VER)/include/spla
   ifeq ($(USE_ACC), yes)
      DFLAGS         += -D__OFFLOAD_GEMM
      SPFFT_LIB      := $(INSTALL_PATH)/SpFFT-$(SPFFT_VER)/lib/cuda
      SPLA_LIB       := $(INSTALL_PATH)/SpLA-$(SPLA_VER)/lib/cuda
      SIRIUS_INC     := $(INSTALL_PATH)/sirius-$(USE_SIRIUS)/include/cuda
      SIRIUS_LIB     := $(INSTALL_PATH)/sirius-$(USE_SIRIUS)/lib/cuda
   else
      SPFFT_LIB      := $(INSTALL_PATH)/SpFFT-$(SPFFT_VER)/lib
      SPLA_LIB       := $(INSTALL_PATH)/SpLA-$(SPLA_VER)/lib
      SIRIUS_INC     := $(INSTALL_PATH)/sirius-$(USE_SIRIUS)/include
      SIRIUS_LIB     := $(INSTALL_PATH)/sirius-$(USE_SIRIUS)/lib
   endif
   CFLAGS         += -I$(LIBVDWXC_INC)
   CFLAGS         += -I$(SPFFT_INC)
   CFLAGS         += -I$(SPLA_INC)
   CFLAGS         += -I$(SIRIUS_INC)
   DFLAGS         += -D__HDF5
   DFLAGS         += -D__LIBVDWXC
   DFLAGS         += -D__SPFFT
   DFLAGS         += -D__SPLA
   DFLAGS         += -D__SIRIUS
   LIBS           += $(SIRIUS_LIB)/libsirius.a
   LIBS           += $(SPLA_LIB)/libspla.a
   LIBS           += $(SPFFT_LIB)/libspfft.a
   LIBS           += $(LIBVDWXC_LIB)/libvdwxc.a
   LIBS           += $(HDF5_LIB)/libhdf5.a
endif

ifneq ($(USE_COSMA),)
   USE_COSMA      := $(strip $(USE_COSMA))
   ifeq ($(USE_ACC), yes)
      USE_COSMA      := $(USE_COSMA)-cuda
   endif
   COSMA_INC      := $(INSTALL_PATH)/COSMA-$(USE_COSMA)/include
   COSMA_LIB      := $(INSTALL_PATH)/COSMA-$(USE_COSMA)/lib
   CFLAGS         += -I$(COSMA_INC)
   DFLAGS         += -D__COSMA
   LIBS           += $(COSMA_LIB)/libcosma_prefixed_pxgemm.a
   LIBS           += $(COSMA_LIB)/libcosma.a
   LIBS           += $(COSMA_LIB)/libcosta_prefixed_scalapack.a
   LIBS           += $(COSMA_LIB)/libcosta.a
   LIBS           += $(COSMA_LIB)/libTiled-MM.a
endif

ifneq ($(USE_GSL),)
   USE_GSL        := $(strip $(USE_GSL))
   GSL_INC        := $(INSTALL_PATH)/gsl-$(USE_GSL)/include
   GSL_LIB        := $(INSTALL_PATH)/gsl-$(USE_GSL)/lib
   CFLAGS         += -I$(GSL_INC)
   DFLAGS         += -D__GSL
   LIBS           += $(GSL_LIB)/libgsl.a
endif

CFLAGS         += $(DFLAGS)

CXXFLAGS       := $(CFLAGS) -std=c++11

OFFLOAD_FLAGS  := $(DFLAGS) -O3 -Xcompiler="-fopenmp" -arch sm_60 --std=c++11

FCFLAGS        := $(CFLAGS)
ifeq ($(shell [ $(shell gcc -dumpversion | cut -d. -f1) -gt 9 ] && echo yes), yes)
   FCFLAGS        += -fallow-argument-mismatch
endif
FCFLAGS        += -fbacktrace
FCFLAGS        += -ffree-form
FCFLAGS        += -ffree-line-length-none
FCFLAGS        += -fno-omit-frame-pointer
FCFLAGS        += -std=f2008

ifneq ($(CUDA_HOME),)
   CUDA_LIB       := $(CUDA_HOME)/lib64
   LDFLAGS        := $(FCFLAGS) -L$(CUDA_LIB) -Wl,-rpath=$(CUDA_LIB)
else
   LDFLAGS        := $(FCFLAGS)
endif

LIBS           += -lcusolver -lcudart -lnvrtc -lcuda -lcufft -lcublas -lrt
LIBS           += -lz -ldl -lpthread -lstdc++

# End
############### END ARCHITECTURE FILE ################


===== TESTS (description) =====
 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-32 RI-RPA/RI-MP2 correlation energy
 input file: benchmarks/QS_mp2_rpa/32-H2O/RI-RPA.inp
 required files: ['benchmarks/QS_mp2_rpa/32-H2O/BASIS_H2O', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32.xyz', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32-PBE-TZ.inp', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32-RI-dRPA-TZ.inp']
 output file: result.log
 # nodes = 8
 # ranks/node = 2
 # threads/rank = 6
 nrepeat = 1
 time[min] = 15
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/01
 job id: 43569182
 --- Point ---
 name: 10
 plot: h2o_32_ri_rpa_mp2
 regex: Total RI-RPA Time= 
 label: RI-RPA (8n/2r/6t)
 --- Point ---
 name: 11
 plot: h2o_32_ri_rpa_mp2_mem
 regex: Estimated peak process memory 
 label: RI-RPA (8n/2r/6t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-32 RI-RPA/RI-MP2 correlation energy
 input file: benchmarks/QS_mp2_rpa/32-H2O/RI-MP2.inp
 required files: ['benchmarks/QS_mp2_rpa/32-H2O/BASIS_H2O', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32.xyz', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32-PBE-TZ.inp', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32-HF-TZ.inp', 'benchmarks/QS_mp2_rpa/32-H2O/H2O-32-RI-MP2-TZ.inp']
 output file: result.log
 # nodes = 8
 # ranks/node = 6
 # threads/rank = 2
 nrepeat = 1
 time[min] = 15
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/02
 job id: 43569184
 --- Point ---
 name: 20
 plot: h2o_32_ri_rpa_mp2
 regex: Total MP2 Time= 
 label: RI-MP2 (8n/6r/2t)
 --- Point ---
 name: 21
 plot: h2o_32_ri_rpa_mp2_mem
 regex: Estimated peak process memory 
 label: RI-MP2 (8n/6r/2t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-64 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-64.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 12
 # threads/rank = 1
 nrepeat = 1
 time[min] = 5
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/03
 job id: 43569188
 --- Point ---
 name: 100
 plot: h2o_64_md
 regex: CP2K  
 label: (8n/12r/1t)
 --- Point ---
 name: 101
 plot: h2o_64_md_mem
 regex: Estimated peak process memory 
 label: (8n/12r/1t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-64 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-64.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 6
 # threads/rank = 2
 nrepeat = 1
 time[min] = 5
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/04
 job id: 43569189
 --- Point ---
 name: 102
 plot: h2o_64_md
 regex: CP2K  
 label: (8n/6r/2t)
 --- Point ---
 name: 103
 plot: h2o_64_md_mem
 regex: Estimated peak process memory 
 label: (8n/6r/2t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-64 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-64.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 4
 # threads/rank = 3
 nrepeat = 1
 time[min] = 5
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/05
 job id: 43569192
 --- Point ---
 name: 104
 plot: h2o_64_md
 regex: CP2K  
 label: (8n/4r/3t)
 --- Point ---
 name: 105
 plot: h2o_64_md_mem
 regex: Estimated peak process memory 
 label: (8n/4r/3t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-64 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-64.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 3
 # threads/rank = 4
 nrepeat = 1
 time[min] = 5
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/06
 job id: 43569193
 --- Point ---
 name: 106
 plot: h2o_64_md
 regex: CP2K  
 label: (8n/3r/4t)
 --- Point ---
 name: 107
 plot: h2o_64_md_mem
 regex: Estimated peak process memory 
 label: (8n/3r/4t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-64 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-64.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 2
 # threads/rank = 6
 nrepeat = 1
 time[min] = 5
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/07
 job id: 43569196
 --- Point ---
 name: 108
 plot: h2o_64_md
 regex: CP2K  
 label: (8n/2r/6t)
 --- Point ---
 name: 109
 plot: h2o_64_md_mem
 regex: Estimated peak process memory 
 label: (8n/2r/6t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-64 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-64.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 1
 # threads/rank = 12
 nrepeat = 1
 time[min] = 5
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/08
 job id: 43569197
 --- Point ---
 name: 110
 plot: h2o_64_md
 regex: CP2K  
 label: (8n/1r/12t)
 --- Point ---
 name: 111
 plot: h2o_64_md_mem
 regex: Estimated peak process memory 
 label: (8n/1r/12t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-128 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-128.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 12
 # threads/rank = 1
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/09
 job id: 43569199
 --- Point ---
 name: 200
 plot: h2o_128_md
 regex: CP2K  
 label: (8n/12r/1t)
 --- Point ---
 name: 201
 plot: h2o_128_md_mem
 regex: Estimated peak process memory 
 label: (8n/12r/1t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-128 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-128.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 6
 # threads/rank = 2
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/10
 job id: 43569200
 --- Point ---
 name: 202
 plot: h2o_128_md
 regex: CP2K  
 label: (8n/6r/2t)
 --- Point ---
 name: 203
 plot: h2o_128_md_mem
 regex: Estimated peak process memory 
 label: (8n/6r/2t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-128 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-128.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 4
 # threads/rank = 3
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/11
 job id: 43569201
 --- Point ---
 name: 204
 plot: h2o_128_md
 regex: CP2K  
 label: (8n/4r/3t)
 --- Point ---
 name: 205
 plot: h2o_128_md_mem
 regex: Estimated peak process memory 
 label: (8n/4r/3t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-128 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-128.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 3
 # threads/rank = 4
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/12
 job id: 43569202
 --- Point ---
 name: 206
 plot: h2o_128_md
 regex: CP2K  
 label: (8n/3r/4t)
 --- Point ---
 name: 207
 plot: h2o_128_md_mem
 regex: Estimated peak process memory 
 label: (8n/3r/4t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-128 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-128.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 2
 # threads/rank = 6
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/13
 job id: 43569203
 --- Point ---
 name: 208
 plot: h2o_128_md
 regex: CP2K  
 label: (8n/2r/6t)
 --- Point ---
 name: 209
 plot: h2o_128_md_mem
 regex: Estimated peak process memory 
 label: (8n/2r/6t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-128 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-128.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 1
 # threads/rank = 12
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/14
 job id: 43569204
 --- Point ---
 name: 210
 plot: h2o_128_md
 regex: CP2K  
 label: (8n/1r/12t)
 --- Point ---
 name: 211
 plot: h2o_128_md_mem
 regex: Estimated peak process memory 
 label: (8n/1r/12t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-256 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-256.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 12
 # threads/rank = 1
 nrepeat = 1
 time[min] = 30
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/15
 job id: 43569205
 --- Point ---
 name: 400
 plot: h2o_256_md
 regex: CP2K  
 label: (8n/12r/1t)
 --- Point ---
 name: 401
 plot: h2o_256_md_mem
 regex: Estimated peak process memory 
 label: (8n/12r/1t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-256 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-256.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 6
 # threads/rank = 2
 nrepeat = 1
 time[min] = 30
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/16
 job id: 43569206
 --- Point ---
 name: 402
 plot: h2o_256_md
 regex: CP2K  
 label: (8n/6r/2t)
 --- Point ---
 name: 403
 plot: h2o_256_md_mem
 regex: Estimated peak process memory 
 label: (8n/6r/2t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-256 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-256.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 4
 # threads/rank = 3
 nrepeat = 1
 time[min] = 30
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/17
 job id: 43569208
 --- Point ---
 name: 404
 plot: h2o_256_md
 regex: CP2K  
 label: (8n/4r/3t)
 --- Point ---
 name: 405
 plot: h2o_256_md_mem
 regex: Estimated peak process memory 
 label: (8n/4r/3t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-256 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-256.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 3
 # threads/rank = 4
 nrepeat = 1
 time[min] = 30
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/18
 job id: 43569209
 --- Point ---
 name: 406
 plot: h2o_256_md
 regex: CP2K  
 label: (8n/3r/4t)
 --- Point ---
 name: 407
 plot: h2o_256_md_mem
 regex: Estimated peak process memory 
 label: (8n/3r/4t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-256 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-256.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 2
 # threads/rank = 6
 nrepeat = 1
 time[min] = 30
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/19
 job id: 43569210
 --- Point ---
 name: 408
 plot: h2o_256_md
 regex: CP2K  
 label: (8n/2r/6t)
 --- Point ---
 name: 409
 plot: h2o_256_md_mem
 regex: Estimated peak process memory 
 label: (8n/2r/6t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-256 test - DBCSR dominated (MPI/OMP)
 input file: benchmarks/QS/H2O-256.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 1
 # threads/rank = 12
 nrepeat = 1
 time[min] = 30
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/20
 job id: 43569211
 --- Point ---
 name: 410
 plot: h2o_256_md
 regex: CP2K  
 label: (8n/1r/12t)
 --- Point ---
 name: 411
 plot: h2o_256_md_mem
 regex: Estimated peak process memory 
 label: (8n/1r/12t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-32 (NREP 3) linear scaling test (864 H2O)
 input file: benchmarks/QS_DM_LS/H2O-dft-ls.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 12
 # threads/rank = 1
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/21
 job id: 43569212
 --- Point ---
 name: 500
 plot: h2o_32_nrep3_ls
 regex: CP2K  
 label: (8n/12r/1t)
 --- Point ---
 name: 501
 plot: h2o_32_nrep3_ls_mem
 regex: Estimated peak process memory 
 label: (8n/12r/1t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-32 (NREP 3) linear scaling test (864 H2O)
 input file: benchmarks/QS_DM_LS/H2O-dft-ls.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 6
 # threads/rank = 2
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/22
 job id: 43569213
 --- Point ---
 name: 502
 plot: h2o_32_nrep3_ls
 regex: CP2K  
 label: (8n/6r/2t)
 --- Point ---
 name: 503
 plot: h2o_32_nrep3_ls_mem
 regex: Estimated peak process memory 
 label: (8n/6r/2t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-32 (NREP 3) linear scaling test (864 H2O)
 input file: benchmarks/QS_DM_LS/H2O-dft-ls.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 4
 # threads/rank = 3
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/23
 job id: 43569214
 --- Point ---
 name: 504
 plot: h2o_32_nrep3_ls
 regex: CP2K  
 label: (8n/4r/3t)
 --- Point ---
 name: 505
 plot: h2o_32_nrep3_ls_mem
 regex: Estimated peak process memory 
 label: (8n/4r/3t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-32 (NREP 3) linear scaling test (864 H2O)
 input file: benchmarks/QS_DM_LS/H2O-dft-ls.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 3
 # threads/rank = 4
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/24
 job id: 43569215
 --- Point ---
 name: 506
 plot: h2o_32_nrep3_ls
 regex: CP2K  
 label: (8n/3r/4t)
 --- Point ---
 name: 507
 plot: h2o_32_nrep3_ls_mem
 regex: Estimated peak process memory 
 label: (8n/3r/4t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-32 (NREP 3) linear scaling test (864 H2O)
 input file: benchmarks/QS_DM_LS/H2O-dft-ls.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 2
 # threads/rank = 6
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/25
 job id: 43569216
 --- Point ---
 name: 508
 plot: h2o_32_nrep3_ls
 regex: CP2K  
 label: (8n/2r/6t)
 --- Point ---
 name: 509
 plot: h2o_32_nrep3_ls_mem
 regex: Estimated peak process memory 
 label: (8n/2r/6t)
 ~~~~~~~ END TEST ~~~~~~~

 ~~~~~~~~~ TEST ~~~~~~~~~
 description: H2O-32 (NREP 3) linear scaling test (864 H2O)
 input file: benchmarks/QS_DM_LS/H2O-dft-ls.inp
 required files: []
 output file: result.log
 # nodes = 8
 # ranks/node = 1
 # threads/rank = 12
 nrepeat = 1
 time[min] = 10
 run dir: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/26
 job id: 43569218
 --- Point ---
 name: 510
 plot: h2o_32_nrep3_ls
 regex: CP2K  
 label: (8n/1r/12t)
 --- Point ---
 name: 511
 plot: h2o_32_nrep3_ls_mem
 regex: Estimated peak process memory 
 label: (8n/1r/12t)
 ~~~~~~~ END TEST ~~~~~~~

=== END TESTS (description) ===


===== PLOTS (description) =====
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_32_ri_rpa_mp2", title="32 H2O molecules (RI-MP2, RI-RPA)", xlabel="Revision", ylabel="Time [s]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_32_ri_rpa_mp2_mem", title="32 H2O molecules (RI-MP2, RI-RPA)", xlabel="Revision", ylabel="Est. peak process memory [MiB]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_64_md", title="64 H2O molecules (10 MD steps)", xlabel="Revision", ylabel="Time [s]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_64_md_mem", title="64 H2O molecules (10 MD steps)", xlabel="Revision", ylabel="Est. peak process memory [MiB]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_128_md", title="128 H2O molecules (10 MD steps)", xlabel="Revision", ylabel="Time [s]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_128_md_mem", title="128 H2O molecules (10 MD steps)", xlabel="Revision", ylabel="Est. peak process memory [MiB]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_256_md", title="256 H2O molecules (10 MD steps)", xlabel="Revision", ylabel="Time [s]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_256_md_mem", title="256 H2O molecules (10 MD steps)", xlabel="Revision", ylabel="Est. peak process memory [MiB]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_32_nrep3_ls", title="864 H2O molecules (LS SCF)", xlabel="Revision", ylabel="Time [s]"
 ~~~~~~~~~ PLOT ~~~~~~~~~
Plot: name="h2o_32_nrep3_ls_mem", title="864 H2O molecules (LS SCF)", xlabel="Revision", ylabel="Est. peak process memory [MiB]"
=== END PLOTS (description) ===


============ RESULTS ============
 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/01/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         0.000000E+00       0.0%      0.0%      0.0%
 flops max/rank                      0.000000E+00       0.0%      0.0%      0.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                                  0       0.0%      0.0%      0.0%
 number of processed stacks                     0       0.0%      0.0%      0.0%
 average stack size                                     0.0       0.0       0.0
 marketing flops                     0.000000E+00
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast                1                     12.
 MP_Allreduce           19                     21.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               15                 177869.
 MP_Allreduce          344                      9.
 MP_Sync                 3
 MP_comm_split           1
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.028    0.042  133.120  133.121
 farming_run                          1  2.0  132.624  132.626  133.072  133.074
 -------------------------------------------------------------------------------


 @@@@@@@@@@ Run number: 2 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32              4194304       0.0%      0.0%    100.0%
 flops    14 x    32 x    32            154140672       0.0%      0.0%    100.0%
 flops    29 x    32 x    32            159645696       0.0%      0.0%    100.0%
 flops    14 x    14 x    32            208732160       0.0%      0.0%    100.0%
 flops    29 x    14 x    32            212860928       0.0%      0.0%    100.0%
 flops    14 x    29 x    32            212860928       0.0%      0.0%    100.0%
 flops    29 x    29 x    32            227352576       0.0%      0.0%    100.0%
 flops    14 x    32 x    14         896801644032       0.0%      0.0%    100.0%
 flops    29 x    32 x    14         928925089792       0.0%      0.0%    100.0%
 flops    14 x    32 x    29         928925089792       0.0%      0.0%    100.0%
 flops    29 x    32 x    29         962100985856       0.0%      0.0%    100.0%
 flops    32 x    32 x    14        1693169221632       0.0%      0.0%    100.0%
 flops    32 x    32 x    29        1753639550976       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         7.164741E+12       0.0%      0.0%    100.0%
 flops max/rank                    447.801317E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          249492158       0.0%      0.0%    100.0%
 number of processed stacks                164328       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1518.3
 marketing flops                     7.165779E+12
 -------------------------------------------------------------------------------
 # multiplications                           1160
 max memory usage/rank               1.455604E+09
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                    2592
 MPI messages size (bytes):
  total size                         1.140326E+09
  min size                           0.000000E+00
  max size                           1.663488E+06
  average size                     439.940750E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                 132                        0
       128 < size <=     8192                 348                  2850816
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                1536                179306496
    131072 < size <=  4194304                 576                958169088
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         2308                     54.
 MP_Alltoall          4670                 822215.
 MP_ISend             2604                  90577.
 MP_IRecv             2604                  90574.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group               12
 MP_Bcast              228                1113141.
 MP_Allreduce          485                2282278.
 MP_Sync                27
 MP_Alltoall            38                9316958.
 MP_SendRecv           120                 384007.
 MP_ISendRecv           45                 235435.
 MP_Wait               191
 MP_comm_split           8
 MP_ISend              127                3867574.
 MP_IRecv              127                3866554.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.010    0.025  115.722  115.723
 qs_energies                          1  2.0    0.000    0.000  115.508  115.509
 mp2_main                             1  3.0    0.000    0.000  113.593  113.594
 mp2_gpw_main                         1  4.0    0.020    0.026  112.769  112.771
 mp2_ri_gpw_compute_in                1  5.0    0.173    0.196   93.742   94.131
 mp2_ri_gpw_compute_in_loop           1  6.0    0.004    0.005   55.502   55.892
 mp2_eri_3c_integrate_gpw           272  7.0    0.153    0.170   41.822   47.176
 get_2c_integrals                     1  6.0    0.001    0.013   37.353   38.044
 integrate_v_rspace                 273  8.0    0.442    0.487   25.163   30.288
 pw_transfer                       6555 10.6    0.377    0.394   27.507   28.274
 fft_wrap_pw1pw2                   5465 11.4    0.044    0.046   26.167   26.822
 grid_integrate_task_list           273  9.0   20.960   26.588   20.960   26.588
 fft_wrap_pw1pw2_100               2178 12.4    1.219    1.426   23.728   24.381
 compute_2c_integrals                 1  7.0    0.022    0.023   19.756   19.756
 compute_2c_integrals_loop_lm         1  8.0    0.003    0.005   18.975   19.444
 mp2_eri_2c_integrate_gpw             1  9.0    2.372    2.436   18.972   19.443
 rpa_ri_compute_en                    1  5.0    0.004    0.005   18.920   19.128
 cp_fm_cholesky_decompose            12  8.2   17.607   18.272   17.607   18.272
 cholesky_decomp                      1  7.0    0.000    0.000   16.445   17.100
 fft3d_s                           5443 13.4   16.239   16.695   16.261   16.717
 ao_to_mo_and_store_B_mult_1        272  7.0   10.846   15.561   10.846   15.561
 calculate_wavefunction             272  8.0    5.411    5.579   12.575   13.157
 rpa_num_int                          1  6.0    0.001    0.007   10.597   10.606
 rpa_num_int_RPA_matrix_operati       8  7.0    0.000    0.000   10.580   10.581
 calc_mat_Q                           8  8.0    0.000    0.000    9.371    9.470
 contract_S_to_Q                      8  9.0    0.000    0.000    8.791    8.887
 calc_potential_gpw                 544  9.5    0.005    0.006    8.269    8.711
 mp2_eri_2c_integrate_gpw_pot_l     272 10.0    0.001    0.002    8.274    8.594
 parallel_gemm_fm                    14  9.1    0.000    0.000    8.380    8.454
 parallel_gemm_fm_cosma              14 10.1    8.380    8.454    8.380    8.454
 potential_pw2rs                    545 10.0    0.107    0.110    7.745    8.441
 create_integ_mat                     1  6.0    0.014    0.026    7.835    7.845
 collocate_single_gaussian          272 10.0    0.041    0.043    7.508    7.762
 array2fm                             1  7.0    0.000    0.000    6.700    7.258
 pw_scatter_s                      2720 13.7    4.434    4.590    4.434    4.590
 pw_gather_s                       2722 13.2    3.904    4.344    3.904    4.344
 array2fm_buffer_send                 1  8.0    2.943    3.131    2.943    3.131
 pw_poisson_solve                   545 10.5    1.127    1.172    2.171    2.413
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="10", plot="h2o_32_ri_rpa_mp2", label="RI-RPA (8n/2r/6t)", y=112.770176, yerr=0.000000
PlotPoint: name="11", plot="h2o_32_ri_rpa_mp2_mem", label="RI-RPA (8n/2r/6t)", y=2728.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/02/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         0.000000E+00       0.0%      0.0%      0.0%
 flops max/rank                      0.000000E+00       0.0%      0.0%      0.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                                  0       0.0%      0.0%      0.0%
 number of processed stacks                     0       0.0%      0.0%      0.0%
 average stack size                                     0.0       0.0       0.0
 marketing flops                     0.000000E+00
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast                1                     12.
 MP_Allreduce           19                     21.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               22                 205321.
 MP_Allreduce          344                     10.
 MP_Sync                 4
 MP_comm_split           1
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.030    0.041  397.324  397.326
 farming_run                          1  2.0  396.355  396.363  397.281  397.283
 -------------------------------------------------------------------------------


 @@@@@@@@@@ Run number: 2 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32             16777216       0.0%      0.0%    100.0%
 flops    14 x    32 x    32            565182464       0.0%      0.0%    100.0%
 flops    29 x    32 x    32            585367552       0.0%      0.0%    100.0%
 flops    14 x    14 x    32            626196480       0.0%      0.0%    100.0%
 flops    29 x    14 x    32            638582784       0.0%      0.0%    100.0%
 flops    14 x    29 x    32            638582784       0.0%      0.0%    100.0%
 flops    29 x    29 x    32            682057728       0.0%      0.0%    100.0%
 flops    14 x    32 x    14         897827141120       0.0%      0.0%    100.0%
 flops    29 x    32 x    14         929989394432       0.0%      0.0%    100.0%
 flops    14 x    32 x    29         929989394432       0.0%      0.0%    100.0%
 flops    29 x    32 x    29         963203301376       0.0%      0.0%    100.0%
 flops    32 x    32 x    14        1693481172992       0.0%      0.0%    100.0%
 flops    32 x    32 x    29        1753962643456       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         7.172206E+12       0.0%      0.0%    100.0%
 flops max/rank                    150.696064E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          249788822       0.0%      0.0%    100.0%
 number of processed stacks                 98736       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    2529.9
 marketing flops                     7.174951E+12
 -------------------------------------------------------------------------------
 # multiplications                           1140
 max memory usage/rank               1.220919E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                   61440
 MPI messages size (bytes):
  total size                         6.073508E+09
  min size                           0.000000E+00
  max size                         642.960000E+03
  average size                      98.852664E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               32004                        0
       128 < size <=     8192                1820                 14909440
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072               18640               1081442304
    131072 < size <=  4194304                8976               4977156096
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         1003                     44.
 MP_Alltoall          1797                 713538.
 MP_ISend             3686                  54943.
 MP_IRecv             3622                  54292.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group               12
 MP_Bcast              703                 408373.
 MP_Allreduce         1821                  23730.
 MP_Sync                38
 MP_Alltoall            77                9739996.
 MP_SendRecv          2876                2171486.
 MP_ISendRecv         1034                 172620.
 MP_Wait              1346
 MP_comm_split           7
 MP_ISend              264                 362227.
 MP_IRecv              264                 362718.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.013    0.031  209.746  209.747
 qs_energies                          1  2.0    0.000    0.000  209.522  209.527
 scf_env_do_scf                       1  3.0    0.000    0.000  106.192  106.192
 qs_ks_update_qs_env                  5  5.0    0.000    0.000  105.265  105.273
 rebuild_ks_matrix                    4  6.0    0.000    0.000  105.264  105.272
 qs_ks_build_kohn_sham_matrix         4  7.0    0.057    0.064  105.264  105.272
 hfx_ks_matrix                        4  8.0    0.001    0.001  104.890  104.893
 integrate_four_center                4  9.0    0.144    0.454  104.889  104.892
 mp2_main                             1  3.0    0.000    0.000  103.043  103.048
 mp2_gpw_main                         1  4.0    0.044    0.068  102.085  102.094
 integrate_four_center_main           4 10.0    0.150    0.645   96.707   99.130
 integrate_four_center_bin          261 11.0   96.557   99.095   96.557   99.095
 init_scf_loop                        1  4.0    0.000    0.000   92.069   92.069
 mp2_ri_gpw_compute_in                1  5.0    0.072    0.118   75.046   76.191
 mp2_ri_gpw_compute_in_loop           1  6.0    0.002    0.003   54.482   55.626
 mp2_eri_3c_integrate_gpw            91  7.0    0.145    0.165   42.238   47.364
 integrate_v_rspace                  95  8.0    0.399    0.566   28.602   33.539
 pw_transfer                       2240 10.6    0.146    0.162   29.845   30.189
 fft_wrap_pw1pw2                   1868 11.4    0.017    0.019   28.870   29.232
 grid_integrate_task_list            95  9.0   23.900   29.034   23.900   29.034
 mp2_ri_gpw_compute_en                1  5.0    0.057    0.068   26.824   28.617
 ao_to_mo_and_store_B_mult_1         91  7.0   10.560   27.090   10.560   27.090
 fft_wrap_pw1pw2_100                730 12.4    1.256    1.435   26.599   26.990
 mp2_ri_gpw_compute_en_RI_loop        1  6.0    1.848    1.913   25.005   25.016
 get_2c_integrals                     1  6.0    0.005    0.024   20.450   20.508
 compute_2c_integrals                 1  7.0    0.012    0.026   19.417   19.444
 compute_2c_integrals_loop_lm         1  8.0    0.009    0.014   18.814   19.247
 mp2_eri_2c_integrate_gpw             1  9.0    1.753    1.857   18.806   19.232
 fft3d_s                           1823 13.4   18.396   18.771   18.410   18.784
 scf_env_do_scf_inner_loop            4  4.0    0.000    0.000   14.118   14.118
 calculate_wavefunction              91  8.0    2.023    2.065    9.745   10.020
 mp2_ri_gpw_compute_en_expansio     172  7.0    0.559    0.585    8.756    9.123
 potential_pw2rs                    186 10.0    0.033    0.034    8.608    9.103
 local_gemm                         172  8.0    8.196    8.576    8.196    8.576
 mp2_eri_2c_integrate_gpw_pot_l      91 10.0    0.001    0.001    8.209    8.514
 mp2_ri_gpw_compute_en_comm          22  7.0    0.503    0.536    8.013    8.357
 calc_potential_gpw                 182  9.5    0.002    0.002    7.900    8.162
 collocate_single_gaussian           91 10.0    0.021    0.068    7.847    8.080
 mp2_ri_gpw_compute_en_ener         172  7.0    6.343    6.430    6.343    6.430
 mp_sendrecv_dm3                   2068  8.0    6.043    6.393    6.043    6.393
 mp_sync                             38 10.4    2.872    5.775    2.872    5.775
 pw_gather_s                        912 13.2    4.914    5.271    4.914    5.271
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="20", plot="h2o_32_ri_rpa_mp2", label="RI-MP2 (8n/6r/2t)", y=102.083090, yerr=0.000000
PlotPoint: name="21", plot="h2o_32_ri_rpa_mp2_mem", label="RI-MP2 (8n/6r/2t)", y=1508.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/03/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                     29.277748E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               5055360       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      29.1
 marketing flops                     2.107592E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             452.419584E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 9436608
 MPI messages size (bytes):
  total size                       333.233553E+09
  min size                           0.000000E+00
  max size                         315.840000E+03
  average size                      35.312852E+03
 MPI breakdown and total messages size (bytes):
             size <=      128             4913240                        0
       128 < size <=     8192             1155432               9465298944
      8192 < size <=    32768             1984512              54190407680
     32768 < size <=   131072              551296              42776657920
    131072 < size <=  4194304              832128             226802306368
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3683                  62385.
 MP_Allreduce        10249                    271.
 MP_Sync               580
 MP_Alltoall          2083                 592243.
 MP_SendRecv         22610                   5520.
 MP_ISendRecv        22610                   5520.
 MP_Wait             37876
 MP_comm_split          50
 MP_ISend            20771                  42672.
 MP_IRecv            20771                  42672.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.018    0.053   53.451   53.452
 qs_mol_dyn_low                       1  2.0    0.004    0.012   53.191   53.198
 qs_forces                           11  3.9    0.002    0.002   53.115   53.117
 qs_energies                         11  4.9    0.001    0.001   51.647   51.658
 scf_env_do_scf                      11  5.9    0.000    0.001   45.534   45.534
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.007   43.395   43.395
 dbcsr_multiply_generic            2286 12.5    0.095    0.098   34.442   34.986
 qs_scf_new_mos                     108  7.5    0.000    0.001   33.274   33.596
 qs_scf_loop_do_ot                  108  8.5    0.000    0.001   33.274   33.596
 ot_scf_mini                        108  9.5    0.002    0.002   31.527   31.750
 multiply_cannon                   2286 13.5    0.183    0.191   26.479   28.404
 multiply_cannon_loop              2286 14.5    1.498    1.575   25.754   27.671
 velocity_verlet                     10  3.0    0.001    0.001   26.466   26.467
 ot_mini                            108 10.5    0.001    0.001   20.170   20.415
 qs_ot_get_derivative               108 11.5    0.001    0.001   17.129   17.323
 mp_waitall_1                    245248 16.5    9.113   16.064    9.113   16.064
 multiply_cannon_metrocomm3       54864 15.5    0.067    0.073    6.381   14.183
 multiply_cannon_multrec          54864 15.5    4.184    6.553    7.597   11.053
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.877    8.012
 qs_ks_build_kohn_sham_matrix       119  9.3    0.010    0.011    7.877    8.012
 mp_sum_l                          7207 12.9    5.949    7.773    5.949    7.773
 multiply_cannon_sync_h2d         54864 15.5    5.820    7.535    5.820    7.535
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.965    7.086
 qs_ot_get_p                        119 10.4    0.001    0.001    6.570    6.916
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    5.859    6.315
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    5.686    5.798
 init_scf_run                        11  5.9    0.000    0.001    4.867    4.867
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    4.867    4.867
 dbcsr_mm_accdrv_process          76910 16.1    1.166    1.818    3.336    4.736
 sum_up_and_integrate               119 10.3    0.012    0.014    4.496    4.505
 integrate_v_rspace                 119 11.3    0.002    0.002    4.484    4.494
 qs_rho_update_rho_low              119  7.7    0.000    0.001    4.152    4.297
 calculate_rho_elec                 119  8.7    0.011    0.016    4.152    4.297
 qs_ot_p2m_diag                      50 11.0    0.004    0.006    3.737    3.836
 multiply_cannon_metrocomm1       54864 15.5    0.051    0.056    2.011    3.473
 calculate_dm_sparse                119  9.5    0.000    0.000    2.957    3.101
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.891    3.100
 apply_single                       119 13.6    0.000    0.000    2.891    3.100
 rs_pw_transfer                     974 11.9    0.011    0.012    2.811    2.940
 jit_kernel_multiply                 13 15.8    2.108    2.868    2.108    2.868
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    2.862    2.862
 ot_diis_step                       108 11.5    0.006    0.006    2.699    2.700
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    2.599    2.688
 calculate_first_density_matrix       1  7.0    0.000    0.001    2.664    2.670
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    2.647    2.647
 cp_fm_redistribute_end              50 14.0    2.407    2.623    2.412    2.624
 cp_fm_diag_elpa_base                50 14.0    0.210    2.531    0.211    2.542
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.379    2.381
 density_rs2pw                      119  9.7    0.004    0.004    2.186    2.299
 acc_transpose_blocks             54864 15.5    0.230    0.249    1.745    2.180
 wfi_extrapolate                     11  7.9    0.001    0.001    2.136    2.136
 init_scf_loop                       11  6.9    0.000    0.000    2.122    2.123
 grid_integrate_task_list           119 12.3    2.010    2.110    2.010    2.110
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.051    2.096
 mp_sum_d                          4125 12.0    1.466    2.091    1.466    2.091
 potential_pw2rs                    119 12.3    0.004    0.004    1.878    1.895
 make_m2s                          4572 13.5    0.055    0.057    1.728    1.770
 pw_transfer                       1439 11.6    0.051    0.056    1.666    1.739
 make_images                       4572 14.5    0.132    0.138    1.643    1.687
 fft_wrap_pw1pw2                   1201 12.6    0.006    0.007    1.591    1.666
 mp_alltoall_d11v                  2130 13.8    1.386    1.563    1.386    1.563
 fft3d_ps                          1201 14.6    0.357    0.463    1.369    1.439
 mp_waitany                       12084 13.8    1.257    1.414    1.257    1.414
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.374    1.393
 grid_collocate_task_list           119  9.7    1.285    1.359    1.285    1.359
 fft_wrap_pw1pw2_140                487 13.2    0.080    0.093    1.216    1.292
 dbcsr_dot_sd                      1205 11.9    0.047    0.058    0.809    1.199
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="100", plot="h2o_64_md", label="(8n/12r/1t)", y=53.452000, yerr=0.000000
PlotPoint: name="101", plot="h2o_64_md_mem", label="(8n/12r/1t)", y=431.181818, yerr=1.113404
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/04/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                     57.173320E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               3066240       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      47.9
 marketing flops                     2.107592E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             488.042496E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 2194560
 MPI messages size (bytes):
  total size                       310.646604E+09
  min size                           0.000000E+00
  max size                           1.145520E+06
  average size                     141.553031E+03
 MPI breakdown and total messages size (bytes):
             size <=      128              724648                        0
       128 < size <=     8192              253512               2076770304
      8192 < size <=    32768              281952               4619501568
     32768 < size <=   131072              494448              39143342080
    131072 < size <=  4194304              440000             264807943488
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3672                  62664.
 MP_Allreduce        10226                    305.
 MP_Sync               104
 MP_Alltoall          2060                2029938.
 MP_SendRecv         16779                  37093.
 MP_ISendRecv        16779                  37093.
 MP_Wait             23539
 MP_comm_split          50
 MP_ISend             5720                 128509.
 MP_IRecv             5720                 128509.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.062    0.078   39.578   39.580
 qs_mol_dyn_low                       1  2.0    0.004    0.009   39.119   39.128
 qs_forces                           11  3.9    0.002    0.002   39.062   39.063
 qs_energies                         11  4.9    0.001    0.007   37.351   37.355
 scf_env_do_scf                      11  5.9    0.001    0.001   32.096   32.097
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   29.498   29.499
 dbcsr_multiply_generic            2286 12.5    0.100    0.102   21.540   21.883
 qs_scf_new_mos                     108  7.5    0.001    0.001   20.348   20.598
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   20.347   20.598
 ot_scf_mini                        108  9.5    0.003    0.006   19.431   19.607
 velocity_verlet                     10  3.0    0.001    0.002   18.500   18.500
 multiply_cannon                   2286 13.5    0.208    0.216   16.334   18.050
 multiply_cannon_loop              2286 14.5    0.903    0.974   15.179   16.492
 ot_mini                            108 10.5    0.001    0.001   11.925   12.167
 mp_waitall_1                    200699 16.5    5.800   10.989    5.800   10.989
 qs_ot_get_derivative               108 11.5    0.001    0.001    9.458    9.640
 multiply_cannon_metrocomm3       27432 15.5    0.068    0.070    4.158    9.477
 multiply_cannon_multrec          27432 15.5    1.974    4.296    5.853    8.530
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.271    7.419
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.016    7.271    7.419
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.412    6.545
 dbcsr_mm_accdrv_process          47894 16.0    3.088    5.174    3.809    5.651
 qs_ot_get_p                        119 10.4    0.001    0.001    4.582    4.820
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    3.654    4.503
 sum_up_and_integrate               119 10.3    0.024    0.027    4.277    4.285
 integrate_v_rspace                 119 11.3    0.002    0.002    4.252    4.262
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    3.050    4.122
 apply_single                       119 13.6    0.000    0.000    3.050    4.121
 mp_sum_l                          7207 12.9    2.149    4.033    2.149    4.033
 init_scf_run                        11  5.9    0.000    0.001    4.013    4.014
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    4.013    4.013
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.707    3.735
 calculate_rho_elec                 119  8.7    0.021    0.024    3.706    3.734
 qs_ot_p2m_diag                      50 11.0    0.009    0.013    3.061    3.080
 make_m2s                          4572 13.5    0.053    0.055    2.640    2.856
 multiply_cannon_sync_h2d         27432 15.5    2.200    2.831    2.200    2.831
 rs_pw_transfer                     974 11.9    0.010    0.011    2.679    2.788
 make_images                       4572 14.5    0.200    0.238    2.550    2.764
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    2.609    2.609
 init_scf_loop                       11  6.9    0.001    0.003    2.576    2.579
 calculate_first_density_matrix       1  7.0    0.000    0.002    2.461    2.462
 ot_diis_step                       108 11.5    0.010    0.011    2.412    2.413
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    2.189    2.281
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    2.260    2.260
 cp_fm_redistribute_end              50 14.0    1.868    2.231    1.872    2.232
 cp_fm_diag_elpa_base                50 14.0    0.345    2.110    0.358    2.165
 density_rs2pw                      119  9.7    0.004    0.004    2.059    2.151
 calculate_dm_sparse                119  9.5    0.000    0.000    2.054    2.135
 potential_pw2rs                    119 12.3    0.006    0.006    2.020    2.034
 grid_integrate_task_list           119 12.3    1.825    1.919    1.825    1.919
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.908    1.910
 pw_transfer                       1439 11.6    0.063    0.067    1.863    1.898
 fft_wrap_pw1pw2                   1201 12.6    0.007    0.008    1.773    1.810
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.678    1.721
 prepare_preconditioner              11  7.9    0.000    0.000    1.640    1.668
 make_preconditioner                 11  8.9    0.000    0.001    1.640    1.668
 make_images_data                  4572 15.5    0.045    0.051    1.193    1.605
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.527    1.586
 jit_kernel_multiply                  8 16.2    0.670    1.569    0.670    1.569
 hybrid_alltoall_any               4725 16.4    0.050    0.111    1.027    1.522
 fft3d_ps                          1201 14.6    0.501    0.553    1.482    1.514
 wfi_extrapolate                     11  7.9    0.001    0.001    1.500    1.500
 acc_transpose_blocks             27432 15.5    0.109    0.115    1.188    1.490
 mp_alltoall_d11v                  2130 13.8    1.259    1.445    1.259    1.445
 fft_wrap_pw1pw2_140                487 13.2    0.075    0.083    1.352    1.389
 mp_allgather_i34                  2286 14.5    0.599    1.372    0.599    1.372
 grid_collocate_task_list           119  9.7    1.239    1.300    1.239    1.300
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.253    1.260
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.209    1.252
 mp_sum_d                          4125 12.0    0.614    1.070    0.614    1.070
 qs_energies_init_hamiltonians       11  5.9    0.000    0.001    0.956    0.958
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.918    0.931
 make_images_sizes                 4572 15.5    0.005    0.005    0.624    0.899
 mp_alltoall_i44                   4572 16.5    0.619    0.895    0.619    0.895
 acc_transpose_blocks_kernels     27432 16.5    0.181    0.270    0.656    0.863
 rs_pw_transfer_PW2RS_50            119 14.3    0.589    0.609    0.790    0.851
 mp_alltoall_z22v                  1201 16.6    0.742    0.815    0.742    0.815
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="102", plot="h2o_64_md", label="(8n/6r/2t)", y=39.580000, yerr=0.000000
PlotPoint: name="103", plot="h2o_64_md_mem", label="(8n/6r/2t)", y=465.000000, yerr=1.651446
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/05/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                     59.051995E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               3143552       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      46.8
 marketing flops                     2.107587E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             522.915840E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                  950976
 MPI messages size (bytes):
  total size                       203.844256E+09
  min size                           0.000000E+00
  max size                           1.638400E+06
  average size                     214.352688E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192              253512               2076770304
      8192 < size <=    32768              179424               2939682816
     32768 < size <=   131072              181440              14863564800
    131072 < size <=  4194304              330176             183964913216
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3672                  62660.
 MP_Allreduce        10225                    303.
 MP_Sync               104
 MP_Alltoall          1821                1607811.
 MP_SendRecv         11067                  57667.
 MP_ISendRecv        11067                  57667.
 MP_Wait             21987
 MP_comm_split          50
 MP_ISend             9880                  92618.
 MP_IRecv             9880                  92618.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.023    0.053   34.002   34.005
 qs_mol_dyn_low                       1  2.0    0.003    0.005   33.628   33.635
 qs_forces                           11  3.9    0.003    0.013   33.567   33.568
 qs_energies                         11  4.9    0.005    0.020   31.969   31.973
 scf_env_do_scf                      11  5.9    0.006    0.041   26.672   26.673
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.006   23.701   23.703
 dbcsr_multiply_generic            2286 12.5    0.094    0.098   17.200   17.295
 velocity_verlet                     10  3.0    0.004    0.010   15.945   15.947
 qs_scf_new_mos                     108  7.5    0.001    0.001   15.384   15.401
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   15.383   15.400
 ot_scf_mini                        108  9.5    0.003    0.004   14.641   14.657
 multiply_cannon                   2286 13.5    0.197    0.201   13.547   14.451
 multiply_cannon_loop              2286 14.5    0.639    0.666   12.693   13.620
 ot_mini                            108 10.5    0.001    0.001    9.068    9.085
 qs_ot_get_derivative               108 11.5    0.001    0.001    7.519    7.532
 multiply_cannon_multrec          18288 15.5    1.943    2.934    7.022    7.393
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.635    6.667
 qs_ks_build_kohn_sham_matrix       119  9.3    0.020    0.047    6.635    6.666
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.898    5.931
 dbcsr_mm_accdrv_process          38222 16.0    4.299    5.611    4.997    5.849
 sum_up_and_integrate               119 10.3    0.030    0.031    4.159    4.164
 integrate_v_rspace                 119 11.3    0.002    0.003    4.129    4.137
 mp_waitall_1                    158411 16.6    2.997    4.076    2.997    4.076
 init_scf_run                        11  5.9    0.000    0.001    3.994    3.994
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    3.994    3.994
 qs_ot_get_p                        119 10.4    0.001    0.001    3.416    3.441
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.422    3.432
 calculate_rho_elec                 119  8.7    0.030    0.031    3.421    3.432
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.799    3.424
 init_scf_loop                       11  6.9    0.005    0.020    2.908    2.910
 calculate_first_density_matrix       1  7.0    0.001    0.004    2.708    2.709
 rs_pw_transfer                     974 11.9    0.009    0.010    2.568    2.667
 multiply_cannon_metrocomm3       18288 15.5    0.044    0.046    1.516    2.459
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.061    2.375
 apply_single                       119 13.6    0.000    0.000    2.061    2.375
 qs_ot_p2m_diag                      50 11.0    0.012    0.012    2.187    2.193
 make_m2s                          4572 13.5    0.046    0.047    1.998    2.131
 jit_kernel_multiply                 10 16.2    0.648    2.110    0.648    2.110
 calculate_dm_sparse                119  9.5    0.001    0.001    2.080    2.102
 density_rs2pw                      119  9.7    0.004    0.004    1.999    2.075
 make_images                       4572 14.5    0.190    0.204    1.911    2.042
 potential_pw2rs                    119 12.3    0.007    0.008    1.923    1.932
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.917    1.919
 prepare_preconditioner              11  7.9    0.000    0.000    1.912    1.917
 make_preconditioner                 11  8.9    0.000    0.002    1.912    1.917
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.913    1.913
 grid_integrate_task_list           119 12.3    1.804    1.912    1.804    1.912
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.756    1.840
 pw_transfer                       1439 11.6    0.064    0.067    1.815    1.831
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.743    1.752
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.724    1.743
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.694    1.699
 mp_sum_l                          7207 12.9    1.279    1.660    1.279    1.660
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.649    1.650
 cp_fm_redistribute_end              50 14.0    1.227    1.621    1.228    1.622
 multiply_cannon_sync_h2d         18288 15.5    1.370    1.583    1.370    1.583
 cp_fm_diag_elpa_base                50 14.0    0.377    1.525    0.391    1.575
 ot_diis_step                       108 11.5    0.011    0.011    1.513    1.513
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.437    1.446
 fft3d_ps                          1201 14.6    0.506    0.522    1.413    1.435
 acc_transpose_blocks             18288 15.5    0.076    0.077    1.337    1.358
 fft_wrap_pw1pw2_140                487 13.2    0.085    0.089    1.305    1.320
 grid_collocate_task_list           119  9.7    1.204    1.318    1.204    1.318
 wfi_extrapolate                     11  7.9    0.001    0.001    1.237    1.237
 make_images_data                  4572 15.5    0.045    0.049    0.886    1.046
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    0.978    0.980
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.913    0.938
 hybrid_alltoall_any               4725 16.4    0.055    0.113    0.766    0.936
 mp_alltoall_d11v                  2130 13.8    0.798    0.909    0.798    0.909
 acc_transpose_blocks_kernels     18288 16.5    0.210    0.220    0.893    0.909
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.823    0.826
 cp_fm_cholesky_invert               11 10.9    0.816    0.821    0.816    0.821
 mp_alltoall_z22v                  1201 16.6    0.735    0.804    0.735    0.804
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.654    0.739
 mp_allgather_i34                  2286 14.5    0.317    0.719    0.317    0.719
 multiply_cannon_metrocomm1       18288 15.5    0.028    0.029    0.410    0.709
 mp_sum_d                          4125 12.0    0.502    0.694    0.502    0.694
 jit_kernel_transpose                 5 15.6    0.683    0.689    0.683    0.689
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="104", plot="h2o_64_md", label="(8n/4r/3t)", y=34.005000, yerr=0.000000
PlotPoint: name="105", plot="h2o_64_md_mem", label="(8n/4r/3t)", y=496.727273, yerr=2.178027
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/06/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                    114.044384E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               3805952       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0      38.6
 marketing flops                     2.107592E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             552.189952E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1042416
 MPI messages size (bytes):
  total size                       150.443262E+09
  min size                           0.000000E+00
  max size                           1.188816E+06
  average size                     144.321719E+03
 MPI breakdown and total messages size (bytes):
             size <=      128              228256                        0
       128 < size <=     8192              126888               1039466496
      8192 < size <=    32768              191472               3137077248
     32768 < size <=   131072              295800              25899827200
    131072 < size <=  4194304              200000             120367247040
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3672                  62659.
 MP_Allreduce        10224                    344.
 MP_Sync               104
 MP_Alltoall          1582                2412273.
 MP_SendRecv          8211                  74133.
 MP_ISendRecv         8211                  74133.
 MP_Wait             16271
 MP_comm_split          50
 MP_ISend             7280                 135929.
 MP_IRecv             7280                 135929.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.038    0.084   35.827   35.828
 qs_mol_dyn_low                       1  2.0    0.003    0.005   35.445   35.452
 qs_forces                           11  3.9    0.002    0.004   35.385   35.387
 qs_energies                         11  4.9    0.009    0.033   33.645   33.650
 scf_env_do_scf                      11  5.9    0.001    0.002   28.495   28.497
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   24.926   24.926
 dbcsr_multiply_generic            2286 12.5    0.100    0.102   18.301   18.451
 velocity_verlet                     10  3.0    0.002    0.002   18.122   18.124
 qs_scf_new_mos                     108  7.5    0.001    0.001   16.521   16.577
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   16.520   16.576
 ot_scf_mini                        108  9.5    0.003    0.006   15.556   15.607
 multiply_cannon                   2286 13.5    0.223    0.260   14.379   14.868
 multiply_cannon_loop              2286 14.5    0.942    0.970   13.366   13.723
 ot_mini                            108 10.5    0.001    0.001    9.369    9.435
 multiply_cannon_multrec          27432 15.5    2.324    2.989    8.571    8.941
 qs_ot_get_derivative               108 11.5    0.001    0.001    7.531    7.583
 dbcsr_mm_accdrv_process          47916 15.9    5.377    7.265    6.154    7.333
 rebuild_ks_matrix                  119  8.3    0.000    0.000    6.631    6.685
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.021    6.631    6.685
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.884    5.932
 sum_up_and_integrate               119 10.3    0.035    0.037    3.871    3.882
 integrate_v_rspace                 119 11.3    0.002    0.004    3.836    3.847
 init_scf_run                        11  5.9    0.000    0.001    3.730    3.730
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    3.730    3.730
 qs_ot_get_p                        119 10.4    0.001    0.001    3.505    3.583
 init_scf_loop                       11  6.9    0.001    0.005    3.548    3.549
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.443    3.476
 calculate_rho_elec                 119  8.7    0.040    0.046    3.442    3.476
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.752    3.222
 prepare_preconditioner              11  7.9    0.000    0.000    2.683    2.690
 make_preconditioner                 11  8.9    0.000    0.001    2.682    2.690
 make_full_inverse_cholesky          11  9.9    0.000    0.000    2.285    2.612
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.119    2.595
 apply_single                       119 13.6    0.000    0.000    2.119    2.595
 make_m2s                          4572 13.5    0.055    0.058    2.403    2.523
 mp_waitall_1                    137007 16.6    1.946    2.505    1.946    2.505
 make_images                       4572 14.5    0.272    0.331    2.293    2.411
 calculate_first_density_matrix       1  7.0    0.001    0.004    2.329    2.331
 rs_pw_transfer                     974 11.9    0.009    0.009    2.167    2.281
 qs_ot_p2m_diag                      50 11.0    0.015    0.023    2.165    2.175
 calculate_dm_sparse                119  9.5    0.001    0.001    2.055    2.115
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.968    1.995
 density_rs2pw                      119  9.7    0.004    0.004    1.867    1.957
 grid_integrate_task_list           119 12.3    1.828    1.904    1.828    1.904
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.858    1.859
 pw_transfer                       1439 11.6    0.063    0.067    1.823    1.853
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.839    1.839
 jit_kernel_multiply                 10 15.8    0.717    1.831    0.717    1.831
 ot_diis_step                       108 11.5    0.012    0.012    1.795    1.795
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.733    1.765
 mp_sum_l                          7207 12.9    1.128    1.677    1.128    1.677
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.654    1.666
 potential_pw2rs                    119 12.3    0.008    0.009    1.642    1.650
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.572    1.573
 cp_fm_redistribute_end              50 14.0    1.041    1.544    1.042    1.545
 cp_fm_diag_elpa_base                50 14.0    0.480    1.471    0.500    1.510
 acc_transpose_blocks             27432 15.5    0.113    0.116    1.450    1.471
 fft3d_ps                          1201 14.6    0.536    0.590    1.414    1.440
 fft_wrap_pw1pw2_140                487 13.2    0.084    0.092    1.390    1.424
 wfi_extrapolate                     11  7.9    0.001    0.001    1.351    1.351
 grid_collocate_task_list           119  9.7    1.220    1.338    1.220    1.338
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.213    1.223
 multiply_cannon_metrocomm3       27432 15.5    0.038    0.039    0.704    1.203
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.141    1.157
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    1.117    1.119
 cp_fm_upper_to_full                 72 13.5    0.802    1.113    0.802    1.113
 dbcsr_complete_redistribute        329 12.2    0.121    0.162    0.814    1.086
 make_images_data                  4572 15.5    0.045    0.049    0.949    1.084
 multiply_cannon_sync_h2d         27432 15.5    0.987    1.055    0.987    1.055
 hybrid_alltoall_any               4725 16.4    0.061    0.152    0.806    0.990
 mp_alltoall_d11v                  2130 13.8    0.852    0.967    0.852    0.967
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.793    0.873
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    0.606    0.871
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.840    0.846
 cp_fm_cholesky_invert               11 10.9    0.833    0.836    0.833    0.836
 acc_transpose_blocks_kernels     27432 16.5    0.267    0.275    0.823    0.831
 mp_alltoall_z22v                  1201 16.6    0.761    0.782    0.761    0.782
 mp_alltoall_i22                    627 13.8    0.439    0.723    0.439    0.723
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="106", plot="h2o_64_md", label="(8n/3r/4t)", y=35.828000, yerr=0.000000
PlotPoint: name="107", plot="h2o_64_md_mem", label="(8n/3r/4t)", y=523.818182, yerr=3.688266
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/07/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                    117.977176E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               1384136       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     106.2
 marketing flops                     2.107587E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             620.339200E+06
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  219456
 MPI messages size (bytes):
  total size                        97.042514E+09
  min size                           0.000000E+00
  max size                           3.276800E+06
  average size                     442.195750E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768              101892               3336634368
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304              116112              93705670464
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         8156                     20.
 MP_Alltoall          8655                  64935.
 MP_ISend            36532                 168375.
 MP_IRecv            36532                 168349.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3672                  62658.
 MP_Allreduce        10224                    344.
 MP_Sync               104
 MP_Alltoall          1582                3682667.
 MP_SendRecv          5355                  94533.
 MP_ISendRecv         5355                  94533.
 MP_Wait             11335
 MP_comm_split          50
 MP_ISend             5200                 225425.
 MP_IRecv             5200                 225425.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.020    0.040   27.934   27.934
 qs_mol_dyn_low                       1  2.0    0.003    0.003   27.737   27.744
 qs_forces                           11  3.9    0.002    0.002   27.679   27.681
 qs_energies                         11  4.9    0.001    0.001   25.985   25.989
 scf_env_do_scf                      11  5.9    0.000    0.001   21.306   21.306
 scf_env_do_scf_inner_loop          108  6.5    0.002    0.006   18.759   18.760
 velocity_verlet                     10  3.0    0.002    0.002   14.278   14.281
 dbcsr_multiply_generic            2286 12.5    0.091    0.093   12.179   12.254
 qs_scf_new_mos                     108  7.5    0.001    0.001   11.118   11.146
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   11.117   11.145
 ot_scf_mini                        108  9.5    0.002    0.002   10.434   10.461
 multiply_cannon                   2286 13.5    0.229    0.241    9.577   10.061
 multiply_cannon_loop              2286 14.5    0.330    0.342    8.655    8.852
 multiply_cannon_multrec           9144 15.5    1.585    1.833    5.780    6.028
 rebuild_ks_matrix                  119  8.3    0.000    0.000    5.840    5.863
 qs_ks_build_kohn_sham_matrix       119  9.3    0.012    0.013    5.839    5.863
 ot_mini                            108 10.5    0.001    0.001    5.731    5.764
 qs_ks_update_qs_env                119  7.6    0.001    0.001    5.208    5.230
 qs_ot_get_derivative               108 11.5    0.001    0.001    4.407    4.435
 dbcsr_mm_accdrv_process          12550 15.8    3.131    4.105    4.093    4.165
 sum_up_and_integrate               119 10.3    0.037    0.041    3.599    3.605
 integrate_v_rspace                 119 11.3    0.003    0.003    3.562    3.568
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.258    3.266
 calculate_rho_elec                 119  8.7    0.059    0.061    3.257    3.266
 init_scf_run                        11  5.9    0.000    0.001    3.232    3.232
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    3.232    3.232
 qs_ot_get_p                        119 10.4    0.001    0.001    2.904    2.956
 init_scf_loop                       11  6.9    0.000    0.000    2.525    2.527
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.109    2.110
 mp_waitall_1                    115863 16.7    1.582    2.070    1.582    2.070
 make_m2s                          4572 13.5    0.035    0.037    1.801    1.983
 qs_ot_p2m_diag                      50 11.0    0.022    0.023    1.953    1.955
 grid_integrate_task_list           119 12.3    1.853    1.906    1.853    1.906
 make_images                       4572 14.5    0.267    0.302    1.710    1.891
 rs_pw_transfer                     974 11.9    0.008    0.008    1.721    1.806
 prepare_preconditioner              11  7.9    0.000    0.000    1.800    1.805
 make_preconditioner                 11  8.9    0.000    0.000    1.800    1.805
 jit_kernel_multiply                 10 15.6    0.924    1.796    0.924    1.796
 calculate_dm_sparse                119  9.5    0.000    0.000    1.770    1.790
 density_rs2pw                      119  9.7    0.003    0.004    1.652    1.754
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.752    1.753
 pw_transfer                       1439 11.6    0.064    0.066    1.743    1.752
 make_full_inverse_cholesky          11  9.9    0.000    0.000    1.683    1.712
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    1.652    1.661
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    1.530    1.550
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.512    1.514
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.455    1.456
 cp_fm_redistribute_end              50 14.0    0.726    1.431    0.727    1.431
 cp_fm_diag_elpa_base                50 14.0    0.658    1.344    0.702    1.413
 potential_pw2rs                    119 12.3    0.010    0.010    1.384    1.388
 grid_collocate_task_list           119  9.7    1.272    1.368    1.272    1.368
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.344    1.353
 fft_wrap_pw1pw2_140                487 13.2    0.082    0.085    1.334    1.346
 fft3d_ps                          1201 14.6    0.539    0.551    1.320    1.328
 ot_diis_step                       108 11.5    0.012    0.013    1.311    1.311
 qs_energies_init_hamiltonians       11  5.9    0.000    0.001    1.232    1.234
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    1.187    1.216
 apply_single                       119 13.6    0.000    0.000    1.187    1.215
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.191    1.206
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.183    1.187
 hybrid_alltoall_any               4725 16.4    0.062    0.176    0.839    1.098
 make_images_data                  4572 15.5    0.039    0.042    0.858    1.082
 wfi_extrapolate                     11  7.9    0.001    0.001    1.079    1.079
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.000    0.868    0.920
 cp_fm_cholesky_invert               11 10.9    0.916    0.919    0.916    0.919
 acc_transpose_blocks              9144 15.5    0.038    0.039    0.891    0.900
 mp_alltoall_d11v                  2130 13.8    0.823    0.884    0.823    0.884
 multiply_cannon_sync_h2d          9144 15.5    0.715    0.802    0.715    0.802
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.753    0.755
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    0.733    0.742
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    0.682    0.734
 mp_allgather_i34                  2286 14.5    0.258    0.696    0.258    0.696
 multiply_cannon_metrocomm3        9144 15.5    0.019    0.019    0.336    0.693
 mp_alltoall_z22v                  1201 16.6    0.655    0.684    0.655    0.684
 acc_transpose_blocks_kernels      9144 16.5    0.116    0.120    0.650    0.656
 qs_create_task_list                 11  7.9    0.006    0.007    0.553    0.578
 generate_qs_task_list               11  8.9    0.190    0.213    0.547    0.572
 dbcsr_complete_redistribute        329 12.2    0.168    0.178    0.537    0.567
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="108", plot="h2o_64_md", label="(8n/2r/6t)", y=27.934000, yerr=0.000000
PlotPoint: name="109", plot="h2o_64_md_mem", label="(8n/2r/6t)", y=584.818182, yerr=8.600404
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/08/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32          26877100032       0.0%      0.0%    100.0%
 flops     9 x     9 x    32          44168260608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32          53835724800       0.0%      0.0%    100.0%
 flops     9 x    22 x    32          53885500416       0.0%      0.0%    100.0%
 flops    32 x    32 x     9          63568871424       0.0%      0.0%    100.0%
 flops    22 x    22 x    32          67007283200       0.0%      0.0%    100.0%
 flops    32 x    32 x    22          77695287296       0.0%      0.0%    100.0%
 flops     9 x    32 x    32          78422999040       0.0%      0.0%    100.0%
 flops    22 x    32 x    32          95850332160       0.0%      0.0%    100.0%
 flops     9 x    32 x     9         266263676928       0.0%      0.0%    100.0%
 flops    22 x    32 x     9         326697440256       0.0%      0.0%    100.0%
 flops     9 x    32 x    22         326697440256       0.0%      0.0%    100.0%
 flops    22 x    32 x    22         399918497792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                         1.880888E+12       0.0%      0.0%    100.0%
 flops max/rank                    235.585836E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          146984760       0.0%      0.0%    100.0%
 number of processed stacks               1388964       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     105.8
 marketing flops                     2.107587E+12
 -------------------------------------------------------------------------------
 # multiplications                           2286
 max memory usage/rank             745.029632E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                   91440
 MPI messages size (bytes):
  total size                        85.748679E+09
  min size                           0.000000E+00
  max size                           6.553600E+06
  average size                     937.758938E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                 572                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768               21148                692256768
     32768 < size <=   131072               19224               1259864064
    131072 < size <=  4194304               41040              21941452800
   4194304 < size <= 16777216                9456              61855174464
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3622                  63729.
 MP_Allreduce        10074                    433.
 MP_Sync                54
 MP_Alltoall          1582                7383731.
 MP_SendRecv          2499                 189067.
 MP_ISendRecv         2499                 189067.
 MP_Wait              6399
 MP_ISend             3120                 546875.
 MP_IRecv             3120                 546875.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.018    0.035   42.040   42.040
 qs_mol_dyn_low                       1  2.0    0.003    0.004   41.831   41.838
 qs_forces                           11  3.9    0.002    0.002   41.771   41.771
 qs_energies                         11  4.9    0.001    0.001   39.816   39.820
 scf_env_do_scf                      11  5.9    0.001    0.001   33.917   33.917
 scf_env_do_scf_inner_loop          108  6.5    0.003    0.006   25.821   25.822
 velocity_verlet                     10  3.0    0.002    0.002   23.528   23.533
 dbcsr_multiply_generic            2286 12.5    0.100    0.101   17.960   18.210
 qs_scf_new_mos                     108  7.5    0.001    0.001   16.654   16.751
 qs_scf_loop_do_ot                  108  8.5    0.001    0.001   16.653   16.750
 ot_scf_mini                        108  9.5    0.002    0.002   15.555   15.650
 multiply_cannon                   2286 13.5    0.304    0.310   13.807   14.784
 multiply_cannon_loop              2286 14.5    0.344    0.351   12.486   13.490
 ot_mini                            108 10.5    0.001    0.001    9.177    9.291
 multiply_cannon_multrec           9144 15.5    3.316    4.545    8.642    8.748
 init_scf_loop                       11  6.9    0.000    0.000    8.067    8.071
 qs_ot_get_derivative               108 11.5    0.001    0.001    7.095    7.186
 rebuild_ks_matrix                  119  8.3    0.000    0.000    7.007    7.151
 qs_ks_build_kohn_sham_matrix       119  9.3    0.013    0.013    7.007    7.150
 prepare_preconditioner              11  7.9    0.000    0.000    7.130    7.145
 make_preconditioner                 11  8.9    0.000    0.000    7.130    7.145
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.657    7.014
 dbcsr_mm_accdrv_process          12550 15.8    4.342    5.777    5.202    6.494
 qs_ks_update_qs_env                119  7.6    0.001    0.001    6.350    6.482
 cp_fm_upper_to_full                 72 14.2    3.176    4.582    3.176    4.582
 init_scf_run                        11  5.9    0.000    0.001    3.868    3.868
 scf_env_initial_rho_setup           11  6.9    0.009    0.009    3.867    3.867
 sum_up_and_integrate               119 10.3    0.064    0.065    3.827    3.834
 qs_rho_update_rho_low              119  7.7    0.001    0.001    3.788    3.796
 calculate_rho_elec                 119  8.7    0.118    0.121    3.788    3.796
 integrate_v_rspace                 119 11.3    0.003    0.003    3.763    3.771
 mp_waitall_1                     94719 16.7    2.641    3.734    2.641    3.734
 qs_ot_get_p                        119 10.4    0.001    0.001    3.562    3.701
 qs_ot_get_derivative_taylor         59 13.0    0.001    0.001    2.666    3.056
 dbcsr_complete_redistribute        329 12.2    0.288    0.292    2.052    2.879
 make_m2s                          4572 13.5    0.039    0.040    2.498    2.691
 make_images                       4572 14.5    0.350    0.381    2.376    2.570
 copy_fm_to_dbcsr                   176 11.2    0.001    0.001    1.720    2.541
 apply_preconditioner_dbcsr         119 12.6    0.000    0.000    2.185    2.486
 apply_single                       119 13.6    0.000    0.000    2.185    2.486
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.411    2.413
 multiply_cannon_metrocomm3        9144 15.5    0.020    0.020    1.411    2.387
 mp_alltoall_i22                    627 13.8    1.463    2.307    1.463    2.307
 calculate_dm_sparse                119  9.5    0.000    0.000    2.285    2.299
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.468    2.281
 qs_ot_p2m_diag                      50 11.0    0.043    0.044    2.166    2.167
 pw_transfer                       1439 11.6    0.067    0.068    2.134    2.138
 grid_integrate_task_list           119 12.3    2.037    2.076    2.037    2.076
 fft_wrap_pw1pw2                   1201 12.6    0.008    0.008    2.038    2.042
 ot_diis_step                       108 11.5    0.014    0.014    2.041    2.041
 density_rs2pw                      119  9.7    0.003    0.003    1.859    1.884
 cp_dbcsr_syevd                      50 12.0    0.003    0.003    1.881    1.882
 mp_sum_l                          7207 12.9    1.116    1.866    1.116    1.866
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    1.828    1.828
 qs_ot_get_derivative_diag           49 12.0    0.001    0.001    1.768    1.814
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    1.758    1.758
 fft3d_ps                          1201 14.6    0.566    0.575    1.673    1.678
 fft_wrap_pw1pw2_140                487 13.2    0.087    0.089    1.672    1.677
 cp_fm_cholesky_invert               11 10.9    1.631    1.634    1.631    1.634
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    1.541    1.569
 cp_fm_diag_elpa                     50 13.0    0.000    0.000    1.568    1.568
 cp_fm_diag_elpa_base                50 14.0    1.420    1.472    1.565    1.565
 hybrid_alltoall_any               4725 16.4    0.086    0.146    1.250    1.523
 rs_pw_transfer                     974 11.9    0.009    0.009    1.497    1.516
 grid_collocate_task_list           119  9.7    1.473    1.491    1.473    1.491
 make_images_data                  4572 15.5    0.043    0.046    1.213    1.463
 wfi_extrapolate                     11  7.9    0.001    0.001    1.389    1.389
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.000    0.000    1.339    1.348
 potential_pw2rs                    119 12.3    0.014    0.014    1.320    1.323
 mp_alltoall_d11v                  2130 13.8    1.227    1.246    1.227    1.246
 qs_ot_get_orbitals                 108 10.5    0.000    0.000    1.195    1.221
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    1.096    1.111
 jit_kernel_multiply                  6 15.5    0.833    1.101    0.833    1.101
 multiply_cannon_sync_h2d          9144 15.5    1.042    1.048    1.042    1.048
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.001    0.988    1.021
 mp_alltoall_z22v                  1201 16.6    0.972    0.995    0.972    0.995
 qs_create_task_list                 11  7.9    0.001    0.001    0.946    0.956
 generate_qs_task_list               11  8.9    0.372    0.393    0.945    0.955
 acc_transpose_blocks              9144 15.5    0.038    0.038    0.892    0.896
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    0.872    0.884
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="110", plot="h2o_64_md", label="(8n/1r/12t)", y=42.040000, yerr=0.000000
PlotPoint: name="111", plot="h2o_64_md_mem", label="(8n/1r/12t)", y=702.727273, yerr=12.008262
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/09/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                    198.287135E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               8410880       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     117.0
 marketing flops                    15.646302E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank             503.140352E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 8483040
 MPI messages size (bytes):
  total size                         1.160510E+12
  min size                           0.000000E+00
  max size                           1.161504E+06
  average size                     136.803609E+03
 MPI breakdown and total messages size (bytes):
             size <=      128             1836752                        0
       128 < size <=     8192             1040592               8524529664
      8192 < size <=    32768             1486976              24362614784
     32768 < size <=   131072             2491776             216971345920
    131072 < size <=  4194304             1626944             910632720448
   4194304 < size <= 16777216                   0                        0
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3521                  65372.
 MP_Allreduce         9840                    486.
 MP_Sync               100
 MP_Alltoall          1938                2392028.
 MP_SendRecv         20900                   9096.
 MP_ISendRecv        20900                   9096.
 MP_Wait             37268
 MP_comm_split          48
 MP_ISend            14300                  82312.
 MP_IRecv            14300                  82312.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.014    0.033   85.407   85.408
 qs_mol_dyn_low                       1  2.0    0.003    0.004   85.129   85.138
 qs_forces                           11  3.9    0.002    0.003   85.061   85.062
 qs_energies                         11  4.9    0.001    0.001   82.193   82.207
 scf_env_do_scf                      11  5.9    0.000    0.001   73.187   73.189
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.007   67.179   67.180
 dbcsr_multiply_generic            2055 12.4    0.107    0.111   53.146   53.366
 qs_scf_new_mos                      99  7.5    0.000    0.001   49.651   49.773
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   49.651   49.773
 ot_scf_mini                         99  9.5    0.002    0.002   47.211   47.326
 multiply_cannon                   2055 13.4    0.178    0.183   42.877   43.859
 velocity_verlet                     10  3.0    0.001    0.002   43.119   43.120
 multiply_cannon_loop              2055 14.4    1.554    1.591   41.762   42.696
 ot_mini                             99 10.5    0.001    0.001   28.505   28.625
 qs_ot_get_derivative                99 11.5    0.001    0.001   21.666   21.785
 multiply_cannon_multrec          49320 15.4   12.085   12.862   17.126   17.801
 rebuild_ks_matrix                  110  8.3    0.000    0.001   14.754   14.856
 qs_ks_build_kohn_sham_matrix       110  9.3    0.011    0.011   14.754   14.856
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.982   13.087
 mp_waitall_1                    220248 16.4   12.070   12.989   12.070   12.989
 multiply_cannon_sync_h2d         49320 15.4    9.890   10.426    9.890   10.426
 qs_ot_get_p                        110 10.4    0.001    0.001   10.035   10.140
 multiply_cannon_metrocomm3       49320 15.4    0.078    0.082    7.000    8.193
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    7.277    7.895
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    7.277    7.862
 apply_single                       110 13.6    0.000    0.001    7.277    7.862
 sum_up_and_integrate               110 10.3    0.036    0.043    7.302    7.315
 integrate_v_rspace                 110 11.3    0.002    0.003    7.265    7.287
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    7.115    7.181
 init_scf_run                        11  5.9    0.000    0.001    6.939    6.939
 scf_env_initial_rho_setup           11  6.9    0.000    0.001    6.938    6.939
 qs_rho_update_rho_low              110  7.6    0.000    0.001    6.624    6.751
 calculate_rho_elec                 110  8.6    0.020    0.024    6.624    6.751
 qs_ot_p2m_diag                      48 11.0    0.012    0.018    6.589    6.622
 ot_diis_step                        99 11.5    0.005    0.006    6.551    6.551
 mp_sum_l                          6514 12.8    5.541    6.507    5.541    6.507
 init_scf_loop                       11  6.9    0.000    0.000    5.974    5.974
 cp_dbcsr_syevd                      48 12.0    0.002    0.003    5.529    5.530
 dbcsr_mm_accdrv_process          87628 16.1    2.083    2.202    4.921    5.243
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    4.939    4.941
 cp_fm_redistribute_end              48 14.0    4.304    4.905    4.308    4.907
 cp_fm_diag_elpa_base                48 14.0    0.591    4.762    0.595    4.784
 make_m2s                          4110 13.4    0.062    0.067    4.274    4.410
 rs_pw_transfer                     902 11.9    0.012    0.013    4.150    4.345
 make_images                       4110 14.4    0.177    0.191    4.176    4.314
 wfi_extrapolate                     11  7.9    0.001    0.001    4.159    4.159
 multiply_cannon_metrocomm1       49320 15.4    0.059    0.063    2.890    4.139
 calculate_dm_sparse                110  9.5    0.000    0.001    3.869    3.944
 density_rs2pw                      110  9.6    0.004    0.004    3.639    3.840
 prepare_preconditioner              11  7.9    0.000    0.000    3.723    3.749
 make_preconditioner                 11  8.9    0.000    0.000    3.723    3.749
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    3.614    3.619
 make_full_inverse_cholesky          11  9.9    0.000    0.000    3.514    3.567
 qs_ot_get_orbitals                  99 10.5    0.000    0.001    3.407    3.454
 grid_integrate_task_list           110 12.3    3.245    3.395    3.245    3.395
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    3.237    3.272
 pw_transfer                       1331 11.6    0.054    0.064    3.134    3.221
 fft_wrap_pw1pw2                   1111 12.6    0.007    0.008    3.046    3.137
 potential_pw2rs                    110 12.3    0.006    0.007    2.852    2.885
 mp_alltoall_d11v                  2046 13.8    2.344    2.783    2.344    2.783
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.685    2.691
 fft3d_ps                          1111 14.6    0.750    0.836    2.586    2.653
 jit_kernel_multiply                 13 15.9    2.553    2.602    2.553    2.602
 fft_wrap_pw1pw2_140                451 13.1    0.167    0.187    2.502    2.598
 acc_transpose_blocks             49320 15.4    0.224    0.236    2.233    2.315
 grid_collocate_task_list           110  9.6    2.086    2.177    2.086    2.177
 mp_waitany                       14300 13.8    1.850    2.142    1.850    2.142
 make_images_data                  4110 15.4    0.042    0.045    1.884    2.019
 cp_fm_cholesky_invert               11 10.9    1.998    2.002    1.998    2.002
 mp_sum_d                          3879 11.9    1.476    1.997    1.476    1.997
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.913    1.940
 hybrid_alltoall_any               4261 16.3    0.081    0.479    1.641    1.939
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.708    1.733
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="200", plot="h2o_128_md", label="(8n/12r/1t)", y=85.408000, yerr=0.000000
PlotPoint: name="201", plot="h2o_128_md_mem", label="(8n/12r/1t)", y=477.181818, yerr=2.917601
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/10/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                    390.715586E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               5019072       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     196.1
 marketing flops                    15.646302E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank             587.042816E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1972800
 MPI messages size (bytes):
  total size                         1.077520E+12
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     546.188250E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               14916                        0
       128 < size <=     8192              222984               1826684928
      8192 < size <=    32768              520356              13399818240
     32768 < size <=   131072              372336              35386294272
    131072 < size <=  4194304              787758             788321309808
   4194304 < size <= 16777216               54450             238588003280
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3521                  65587.
 MP_Allreduce         9839                    562.
 MP_Sync               100
 MP_Alltoall          1717                2075555.
 MP_SendRecv         10340                  26400.
 MP_ISendRecv        10340                  26400.
 MP_Wait             22352
 MP_comm_split          48
 MP_ISend            10164                 155761.
 MP_IRecv            10164                 155761.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.013    0.030   70.858   70.859
 qs_mol_dyn_low                       1  2.0    0.003    0.004   70.626   70.635
 qs_forces                           11  3.9    0.002    0.003   70.504   70.507
 qs_energies                         11  4.9    0.001    0.001   67.108   67.118
 scf_env_do_scf                      11  5.9    0.000    0.001   58.435   58.438
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.007   50.044   50.044
 dbcsr_multiply_generic            2055 12.4    0.114    0.120   38.570   38.789
 velocity_verlet                     10  3.0    0.017    0.045   37.759   37.760
 qs_scf_new_mos                      99  7.5    0.001    0.001   33.754   33.850
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   33.753   33.849
 multiply_cannon                   2055 13.4    0.222    0.243   31.270   32.530
 ot_scf_mini                         99  9.5    0.003    0.003   32.043   32.132
 multiply_cannon_loop              2055 14.4    0.930    0.953   29.798   30.902
 ot_mini                             99 10.5    0.001    0.001   18.823   18.915
 multiply_cannon_multrec          24660 15.4    7.576    9.163   13.759   15.163
 rebuild_ks_matrix                  110  8.3    0.000    0.001   13.929   14.084
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.014   13.929   14.084
 qs_ot_get_derivative                99 11.5    0.001    0.001   12.936   13.027
 qs_ks_update_qs_env                110  7.6    0.001    0.001   12.260   12.397
 mp_waitall_1                    176588 16.5    8.219   11.127    8.219   11.127
 init_scf_loop                       11  6.9    0.000    0.000    8.351    8.352
 multiply_cannon_metrocomm3       24660 15.4    0.070    0.072    5.368    8.215
 multiply_cannon_sync_h2d         24660 15.4    7.011    8.079    7.011    8.079
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    6.586    7.317
 apply_single                       110 13.6    0.000    0.001    6.586    7.317
 sum_up_and_integrate               110 10.3    0.053    0.058    6.725    6.740
 integrate_v_rspace                 110 11.3    0.002    0.002    6.672    6.687
 qs_ot_get_p                        110 10.4    0.001    0.001    6.443    6.546
 dbcsr_mm_accdrv_process          52282 16.1    4.694    5.488    6.027    6.314
 prepare_preconditioner              11  7.9    0.000    0.000    6.287    6.304
 make_preconditioner                 11  8.9    0.000    0.000    6.287    6.304
 init_scf_run                        11  5.9    0.000    0.001    6.248    6.249
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    6.248    6.248
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.000    6.017
 calculate_rho_elec                 110  8.6    0.039    0.047    5.999    6.016
 make_full_inverse_cholesky          11  9.9    0.000    0.000    5.826    5.988
 ot_diis_step                        99 11.5    0.010    0.010    5.833    5.834
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    4.877    5.589
 make_m2s                          4110 13.4    0.058    0.061    4.574    5.117
 make_images                       4110 14.4    0.398    0.445    4.463    5.001
 qs_ot_p2m_diag                      48 11.0    0.029    0.044    4.369    4.391
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.908    3.908
 wfi_extrapolate                     11  7.9    0.001    0.001    3.657    3.657
 pw_transfer                       1331 11.6    0.066    0.074    3.497    3.637
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.390    3.530
 density_rs2pw                      110  9.6    0.004    0.004    3.260    3.441
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.388    3.440
 rs_pw_transfer                     902 11.9    0.012    0.013    3.155    3.328
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.002    3.285    3.287
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.276    3.278
 grid_integrate_task_list           110 12.3    3.138    3.277    3.138    3.277
 cp_fm_redistribute_end              48 14.0    2.452    3.248    2.454    3.249
 cp_fm_diag_elpa_base                48 14.0    0.760    3.087    0.791    3.178
 make_images_data                  4110 15.4    0.046    0.051    2.588    3.143
 calculate_dm_sparse                110  9.5    0.001    0.001    3.052    3.085
 hybrid_alltoall_any               4261 16.3    0.101    0.440    2.249    3.057
 cp_fm_cholesky_invert               11 10.9    3.005    3.013    3.005    3.013
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.897    2.962
 fft_wrap_pw1pw2_140                451 13.1    0.199    0.218    2.755    2.890
 fft3d_ps                          1111 14.6    1.071    1.263    2.748    2.876
 mp_sum_l                          6514 12.8    2.104    2.810    2.104    2.810
 potential_pw2rs                    110 12.3    0.008    0.009    2.557    2.573
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.493    2.497
 mp_alltoall_d11v                  2046 13.8    2.000    2.248    2.000    2.248
 grid_collocate_task_list           110  9.6    2.119    2.248    2.119    2.248
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    2.044    2.063
 mp_allgather_i34                  2055 14.4    0.801    1.946    0.801    1.946
 qs_energies_init_hamiltonians       11  5.9    0.000    0.001    1.873    1.876
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.835    1.859
 jit_kernel_multiply                  9 16.3    0.983    1.807    0.983    1.807
 multiply_cannon_metrocomm4       22605 15.4    0.072    0.075    0.774    1.662
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.605    1.621
 dbcsr_complete_redistribute        325 12.2    0.242    0.307    1.320    1.598
 cp_fm_cholesky_decompose            22 10.9    1.573    1.579    1.573    1.579
 acc_transpose_blocks             24660 15.4    0.110    0.112    1.511    1.544
 mp_alltoall_z22v                  1111 16.6    1.398    1.479    1.398    1.479
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.001    1.368    1.478
 mp_irecv_dv                      57340 16.2    0.652    1.445    0.652    1.445
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="202", plot="h2o_128_md", label="(8n/6r/2t)", y=70.859000, yerr=0.000000
PlotPoint: name="203", plot="h2o_128_md_mem", label="(8n/6r/2t)", y=554.181818, yerr=6.603280
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/11/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                    404.681598E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               3346752       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     294.1
 marketing flops                    15.646297E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank             660.811776E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                  854880
 MPI messages size (bytes):
  total size                       708.322787E+09
  min size                           0.000000E+00
  max size                           6.553600E+06
  average size                     828.564000E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768              222984               7302414336
     32768 < size <=   131072              153888              10085203968
    131072 < size <=  4194304              389376             200257044480
   4194304 < size <= 16777216               82208             490679162176
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3521                  65578.
 MP_Allreduce         9838                    559.
 MP_Sync               100
 MP_Alltoall          1496                4511006.
 MP_SendRecv          6820                  27424.
 MP_ISendRecv         6820                  27424.
 MP_Wait             25498
 MP_comm_split          48
 MP_ISend            17072                 115022.
 MP_IRecv            17072                 115022.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.058    0.150   60.230   60.232
 qs_mol_dyn_low                       1  2.0    0.003    0.004   59.739   59.748
 qs_forces                           11  3.9    0.012    0.023   59.661   59.662
 qs_energies                         11  4.9    0.004    0.013   56.501   56.513
 scf_env_do_scf                      11  5.9    0.001    0.001   48.241   48.241
 scf_env_do_scf_inner_loop           99  6.5    0.003    0.006   39.583   39.584
 velocity_verlet                     10  3.0    0.009    0.018   32.372   32.373
 dbcsr_multiply_generic            2055 12.4    0.108    0.112   28.807   29.053
 qs_scf_new_mos                      99  7.5    0.001    0.001   25.069   25.159
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   25.068   25.158
 ot_scf_mini                         99  9.5    0.003    0.003   23.842   23.957
 multiply_cannon                   2055 13.4    0.211    0.223   22.426   23.748
 multiply_cannon_loop              2055 14.4    0.618    0.636   21.265   22.349
 ot_mini                             99 10.5    0.001    0.001   13.570   13.685
 rebuild_ks_matrix                  110  8.3    0.000    0.001   12.157   12.282
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.015   12.156   12.282
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.778   10.910
 multiply_cannon_multrec          16440 15.4    3.908    5.046    9.922   10.862
 mp_waitall_1                    139946 16.5    7.143   10.118    7.143   10.118
 qs_ot_get_derivative                99 11.5    0.001    0.001    9.147    9.261
 init_scf_loop                       11  6.9    0.001    0.005    8.623    8.624
 multiply_cannon_metrocomm3       16440 15.4    0.043    0.045    4.338    7.087
 prepare_preconditioner              11  7.9    0.000    0.000    6.773    6.790
 make_preconditioner                 11  8.9    0.000    0.001    6.773    6.790
 make_full_inverse_cholesky          11  9.9    0.000    0.000    6.108    6.465
 sum_up_and_integrate               110 10.3    0.061    0.062    6.368    6.384
 integrate_v_rspace                 110 11.3    0.002    0.003    6.308    6.322
 dbcsr_mm_accdrv_process          34862 16.1    4.876    5.653    5.868    6.051
 init_scf_run                        11  5.9    0.000    0.001    5.800    5.801
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    5.800    5.801
 qs_ot_get_p                        110 10.4    0.001    0.001    5.446    5.577
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.567    5.575
 calculate_rho_elec                 110  8.6    0.058    0.058    5.566    5.575
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.924    5.374
 apply_single                       110 13.6    0.000    0.000    4.924    5.374
 make_m2s                          4110 13.4    0.051    0.053    4.271    4.613
 make_images                       4110 14.4    0.391    0.510    4.154    4.495
 ot_diis_step                        99 11.5    0.010    0.011    4.393    4.393
 multiply_cannon_sync_h2d         16440 15.4    3.716    4.344    3.716    4.344
 qs_ot_p2m_diag                      48 11.0    0.042    0.044    3.832    3.836
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.173    3.803
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.489    3.490
 grid_integrate_task_list           110 12.3    3.199    3.346    3.199    3.346
 pw_transfer                       1331 11.6    0.065    0.071    3.185    3.193
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.078    3.090
 density_rs2pw                      110  9.6    0.004    0.004    2.829    3.012
 make_images_data                  4110 15.4    0.043    0.048    2.520    2.961
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    2.951    2.952
 wfi_extrapolate                     11  7.9    0.001    0.001    2.947    2.947
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.938    2.940
 hybrid_alltoall_any               4261 16.3    0.105    0.374    2.238    2.935
 cp_fm_redistribute_end              48 14.0    1.842    2.927    1.844    2.927
 rs_pw_transfer                     902 11.9    0.011    0.012    2.691    2.905
 cp_fm_diag_elpa_base                48 14.0    1.020    2.781    1.079    2.885
 calculate_first_density_matrix       1  7.0    0.001    0.004    2.771    2.773
 calculate_dm_sparse                110  9.5    0.001    0.001    2.679    2.709
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.613    2.665
 cp_fm_cholesky_invert               11 10.9    2.645    2.651    2.645    2.651
 fft_wrap_pw1pw2_140                451 13.1    0.210    0.212    2.631    2.643
 fft3d_ps                          1111 14.6    1.063    1.070    2.392    2.400
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.327    2.392
 multiply_cannon_metrocomm4       14385 15.4    0.044    0.048    0.878    2.352
 grid_collocate_task_list           110  9.6    2.178    2.310    2.178    2.310
 mp_irecv_dv                      48980 15.7    0.808    2.229    0.808    2.229
 potential_pw2rs                    110 12.3    0.010    0.011    2.204    2.215
 mp_alltoall_d11v                  2046 13.8    1.799    2.098    1.799    2.098
 mp_sum_l                          6514 12.8    1.531    2.088    1.531    2.088
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    2.000    2.011
 dbcsr_complete_redistribute        325 12.2    0.326    0.370    1.432    1.896
 cp_fm_upper_to_full                 70 13.6    1.390    1.862    1.390    1.862
 jit_kernel_multiply                  8 16.6    0.604    1.776    0.604    1.776
 mp_allgather_i34                  2055 14.4    0.488    1.678    0.488    1.678
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.634    1.647
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.634    1.647
 cp_fm_cholesky_decompose            22 10.9    1.609    1.626    1.609    1.626
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.001    1.364    1.469
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    0.977    1.424
 mp_waitany                       17072 13.8    1.150    1.371    1.150    1.371
 acc_transpose_blocks             16440 15.4    0.071    0.074    1.272    1.284
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.257    1.267
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="204", plot="h2o_128_md", label="(8n/4r/3t)", y=60.232000, yerr=0.000000
PlotPoint: name="205", plot="h2o_128_md_mem", label="(8n/4r/3t)", y=625.090909, yerr=9.404588
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/12/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                    601.317074E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               4916280       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     200.2
 marketing flops                    15.646302E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank             729.354240E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                  937080
 MPI messages size (bytes):
  total size                       523.723932E+09
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     558.889250E+03
 MPI breakdown and total messages size (bytes):
             size <=      128                6996                        0
       128 < size <=     8192                 264                  2162688
      8192 < size <=    32768              304932               8165326848
     32768 < size <=   131072              110640               6338641920
    131072 < size <=  4194304              489498             400769458320
   4194304 < size <= 16777216               24750             108449092400
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3521                  65576.
 MP_Allreduce         9838                    600.
 MP_Sync               100
 MP_Alltoall          1496                5863162.
 MP_SendRecv          5060                  43184.
 MP_ISendRecv         5060                  43184.
 MP_Wait             20042
 MP_comm_split          48
 MP_ISend            13376                 163145.
 MP_IRecv            13376                 163145.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.052    0.081   65.005   65.007
 qs_mol_dyn_low                       1  2.0    0.003    0.004   64.614   64.623
 qs_forces                           11  3.9    0.002    0.004   64.545   64.547
 qs_energies                         11  4.9    0.002    0.005   61.174   61.178
 scf_env_do_scf                      11  5.9    0.001    0.001   52.764   52.767
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.006   40.741   40.741
 velocity_verlet                     10  3.0    0.004    0.005   36.950   36.952
 dbcsr_multiply_generic            2055 12.4    0.116    0.119   29.565   29.811
 qs_scf_new_mos                      99  7.5    0.001    0.001   26.332   26.437
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   26.332   26.437
 ot_scf_mini                         99  9.5    0.003    0.004   24.700   24.803
 multiply_cannon                   2055 13.4    0.243    0.266   22.424   23.630
 multiply_cannon_loop              2055 14.4    0.886    0.904   20.987   21.622
 ot_mini                             99 10.5    0.001    0.001   14.099   14.209
 multiply_cannon_multrec          24660 15.4    4.183    6.576   12.607   13.977
 rebuild_ks_matrix                  110  8.3    0.000    0.000   11.970   12.094
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.013   11.969   12.093
 init_scf_loop                       11  6.9    0.000    0.001   11.981   11.981
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.599   10.709
 prepare_preconditioner              11  7.9    0.000    0.000   10.112   10.127
 make_preconditioner                 11  8.9    0.003    0.014   10.112   10.127
 qs_ot_get_derivative                99 11.5    0.001    0.001    9.929   10.029
 make_full_inverse_cholesky          11  9.9    0.000    0.000    8.349    9.779
 dbcsr_mm_accdrv_process          52304 16.0    6.688    8.352    8.278    9.227
 mp_waitall_1                    121746 16.5    4.426    6.504    4.426    6.504
 sum_up_and_integrate               110 10.3    0.068    0.070    6.337    6.351
 integrate_v_rspace                 110 11.3    0.002    0.003    6.269    6.284
 make_m2s                          4110 13.4    0.061    0.063    5.523    5.884
 qs_ot_get_p                        110 10.4    0.001    0.001    5.629    5.775
 make_images                       4110 14.4    0.574    0.689    5.379    5.736
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.636    5.643
 init_scf_run                        11  5.9    0.000    0.001    5.642    5.643
 calculate_rho_elec                 110  8.6    0.077    0.081    5.636    5.642
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    5.642    5.642
 cp_fm_upper_to_full                 70 13.8    3.246    4.609    3.246    4.609
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.041    4.136
 apply_single                       110 13.6    0.000    0.000    4.041    4.136
 ot_diis_step                        99 11.5    0.011    0.011    4.129    4.129
 dbcsr_complete_redistribute        325 12.2    0.417    0.459    2.700    3.832
 qs_ot_p2m_diag                      48 11.0    0.055    0.063    3.789    3.803
 grid_integrate_task_list           110 12.3    3.275    3.405    3.275    3.405
 multiply_cannon_metrocomm3       24660 15.4    0.035    0.036    1.484    3.385
 multiply_cannon_sync_h2d         24660 15.4    3.174    3.353    3.174    3.353
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    3.307    3.349
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.306    3.306
 pw_transfer                       1331 11.6    0.065    0.072    3.275    3.303
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    2.150    3.266
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.169    3.200
 make_images_data                  4110 15.4    0.046    0.050    2.776    3.197
 hybrid_alltoall_any               4261 16.3    0.119    0.458    2.416    3.144
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    3.038    3.094
 density_rs2pw                      110  9.6    0.004    0.004    2.784    2.982
 wfi_extrapolate                     11  7.9    0.001    0.001    2.969    2.970
 calculate_dm_sparse                110  9.5    0.001    0.001    2.919    2.945
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.939    2.942
 cp_fm_cholesky_invert               11 10.9    2.897    2.906    2.897    2.906
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    1.750    2.849
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    2.772    2.774
 mp_alltoall_i22                    605 13.7    1.627    2.771    1.627    2.771
 cp_fm_redistribute_end              48 14.0    1.387    2.744    1.388    2.745
 fft_wrap_pw1pw2_140                451 13.1    0.201    0.213    2.684    2.717
 cp_fm_diag_elpa_base                48 14.0    1.275    2.605    1.353    2.715
 rs_pw_transfer                     902 11.9    0.010    0.011    2.461    2.670
 calculate_first_density_matrix       1  7.0    0.000    0.002    2.587    2.588
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.542    2.582
 fft3d_ps                          1111 14.6    1.062    1.098    2.473    2.491
 grid_collocate_task_list           110  9.6    2.223    2.345    2.223    2.345
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    2.266    2.268
 jit_kernel_multiply                 12 15.7    1.261    2.203    1.261    2.203
 potential_pw2rs                    110 12.3    0.012    0.013    2.125    2.133
 mp_alltoall_d11v                  2046 13.8    1.850    1.996    1.850    1.996
 cp_fm_cholesky_decompose            22 10.9    1.715    1.773    1.715    1.773
 qs_ot_get_orbitals                  99 10.5    0.001    0.001    1.717    1.750
 build_core_hamiltonian_matrix_      11  4.9    0.000    0.001    1.601    1.703
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.616    1.630
 multiply_cannon_metrocomm4       20550 15.4    0.057    0.060    0.858    1.585
 mp_allgather_i34                  2055 14.4    0.544    1.558    0.544    1.558
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.526    1.541
 acc_transpose_blocks             24660 15.4    0.106    0.108    1.497    1.521
 mp_irecv_dv                      62702 16.1    0.759    1.508    0.759    1.508
 mp_sum_l                          6514 12.8    0.958    1.460    0.958    1.460
 mp_waitany                       13376 13.8    1.068    1.349    1.068    1.349
 qs_env_update_s_mstruct             11  6.9    0.000    0.001    1.220    1.318
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="206", plot="h2o_128_md", label="(8n/3r/4t)", y=65.007000, yerr=0.000000
PlotPoint: name="207", plot="h2o_128_md_mem", label="(8n/3r/4t)", y=691.090909, yerr=9.433543
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/13/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                    807.299199E+09       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               1438408       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     684.2
 marketing flops                    15.646297E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank             833.867776E+06
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  197280
 MPI messages size (bytes):
  total size                       339.125567E+09
  min size                           0.000000E+00
  max size                          13.107200E+06
  average size                       1.719006E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 132                  4325376
     32768 < size <=   131072               88656              11620319232
    131072 < size <=  4194304               89424             117209825280
   4194304 < size <= 16777216               17616             210291069504
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         7346                     33.
 MP_Alltoall          8043                 263767.
 MP_ISend            32836                 654203.
 MP_IRecv            32836                 654587.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3521                  65574.
 MP_Allreduce         9838                    640.
 MP_Sync               100
 MP_Alltoall          1496                8504061.
 MP_SendRecv          3300                  54848.
 MP_ISendRecv         3300                  54848.
 MP_Wait             13926
 MP_comm_split          48
 MP_ISend             9240                 278857.
 MP_IRecv             9240                 278857.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.016    0.032   56.447   56.447
 qs_mol_dyn_low                       1  2.0    0.003    0.004   56.160   56.169
 qs_forces                           11  3.9    0.002    0.002   56.091   56.092
 qs_energies                         11  4.9    0.001    0.001   52.440   52.444
 scf_env_do_scf                      11  5.9    0.000    0.001   43.800   43.800
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.006   35.370   35.371
 velocity_verlet                     10  3.0    0.002    0.002   31.789   31.792
 dbcsr_multiply_generic            2055 12.4    0.105    0.107   23.039   23.143
 qs_scf_new_mos                      99  7.5    0.001    0.001   21.053   21.103
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   21.053   21.103
 ot_scf_mini                         99  9.5    0.002    0.002   19.790   19.819
 multiply_cannon                   2055 13.4    0.249    0.272   17.338   18.698
 multiply_cannon_loop              2055 14.4    0.321    0.334   15.990   16.292
 rebuild_ks_matrix                  110  8.3    0.000    0.000   11.593   11.611
 qs_ks_build_kohn_sham_matrix       110  9.3    0.012    0.013   11.593   11.611
 ot_mini                             99 10.5    0.001    0.001   10.536   10.557
 qs_ks_update_qs_env                110  7.6    0.001    0.001   10.325   10.339
 multiply_cannon_multrec           8220 15.4    3.183    4.440    7.477    8.417
 init_scf_loop                       11  6.9    0.000    0.000    8.374    8.376
 mp_waitall_1                    103326 16.6    6.118    7.911    6.118    7.911
 qs_ot_get_derivative                99 11.5    0.001    0.001    6.707    6.733
 prepare_preconditioner              11  7.9    0.000    0.000    6.715    6.720
 make_preconditioner                 11  8.9    0.000    0.000    6.715    6.720
 make_full_inverse_cholesky          11  9.9    0.000    0.000    6.301    6.377
 sum_up_and_integrate               110 10.3    0.080    0.081    6.309    6.322
 integrate_v_rspace                 110 11.3    0.003    0.003    6.229    6.241
 qs_rho_update_rho_low              110  7.6    0.001    0.001    5.752    5.771
 calculate_rho_elec                 110  8.6    0.115    0.116    5.752    5.770
 init_scf_run                        11  5.9    0.000    0.001    5.497    5.498
 scf_env_initial_rho_setup           11  6.9    0.001    0.001    5.497    5.497
 qs_ot_get_p                        110 10.4    0.001    0.001    5.310    5.337
 dbcsr_mm_accdrv_process          17442 15.9    2.902    3.920    4.164    5.052
 make_m2s                          4110 13.4    0.040    0.042    4.307    4.564
 make_images                       4110 14.4    0.634    0.687    4.175    4.430
 multiply_cannon_metrocomm3        8220 15.4    0.017    0.018    2.992    4.365
 qs_ot_p2m_diag                      48 11.0    0.081    0.084    3.886    3.889
 ot_diis_step                        99 11.5    0.012    0.012    3.800    3.801
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    3.711    3.748
 apply_single                       110 13.6    0.000    0.000    3.711    3.748
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.563    3.564
 grid_integrate_task_list           110 12.3    3.356    3.510    3.356    3.510
 pw_transfer                       1331 11.6    0.065    0.070    3.346    3.366
 cp_fm_cholesky_invert               11 10.9    3.322    3.326    3.322    3.326
 fft_wrap_pw1pw2                   1111 12.6    0.008    0.008    3.239    3.263
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.006    3.007
 multiply_cannon_sync_h2d          8220 15.4    2.918    3.004    2.918    3.004
 cp_fm_redistribute_end              48 14.0    0.766    2.974    0.771    2.974
 density_rs2pw                      110  9.6    0.004    0.004    2.788    2.944
 cp_fm_diag_elpa_base                48 14.0    2.015    2.771    2.193    2.937
 make_images_data                  4110 15.4    0.038    0.043    2.415    2.816
 wfi_extrapolate                     11  7.9    0.001    0.001    2.814    2.814
 fft_wrap_pw1pw2_140                451 13.1    0.212    0.215    2.733    2.767
 hybrid_alltoall_any               4261 16.3    0.199    0.863    2.355    2.757
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    2.673    2.674
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.639    2.640
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.578    2.580
 calculate_dm_sparse                110  9.5    0.001    0.001    2.521    2.568
 fft3d_ps                          1111 14.6    1.122    1.167    2.497    2.514
 rs_pw_transfer                     902 11.9    0.010    0.010    2.327    2.495
 grid_collocate_task_list           110  9.6    2.323    2.483    2.323    2.483
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.230    2.239
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    2.024    2.046
 potential_pw2rs                    110 12.3    0.015    0.015    2.021    2.027
 mp_alltoall_d11v                  2046 13.8    1.794    2.005    1.794    2.005
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    1.774    1.998
 cp_fm_cholesky_decompose            22 10.9    1.924    1.943    1.924    1.943
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    1.860    1.876
 dbcsr_complete_redistribute        325 12.2    0.559    0.600    1.545    1.653
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    1.514    1.634
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.602    1.606
 mp_allgather_i34                  2055 14.4    0.534    1.599    0.534    1.599
 jit_kernel_multiply                  8 15.5    0.955    1.482    0.955    1.482
 cp_dbcsr_plus_fm_fm_t_native        22  8.9    0.001    0.001    1.464    1.481
 qs_create_task_list                 11  7.9    0.000    0.001    1.235    1.334
 generate_qs_task_list               11  8.9    0.379    0.448    1.235    1.333
 mp_waitany                        9240 13.8    1.071    1.275    1.071    1.275
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.206    1.226
 mp_alltoall_z22v                  1111 16.6    1.142    1.163    1.142    1.163
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="208", plot="h2o_128_md", label="(8n/2r/6t)", y=56.447000, yerr=0.000000
PlotPoint: name="209", plot="h2o_128_md_mem", label="(8n/2r/6t)", y=784.363636, yerr=11.849609
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/14/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    32 x    32 x    32         184415158272       0.0%      0.0%    100.0%
 flops     9 x     9 x    32         269180485632       0.0%      0.0%    100.0%
 flops     9 x    22 x    32         349395425280       0.0%      0.0%    100.0%
 flops    22 x     9 x    32         350042406912       0.0%      0.0%    100.0%
 flops    22 x    22 x    32         453581815808       0.0%      0.0%    100.0%
 flops    32 x    32 x     9         465064427520       0.0%      0.0%    100.0%
 flops    32 x    32 x    22         568412078080       0.0%      0.0%    100.0%
 flops     9 x    32 x    32         572195340288       0.0%      0.0%    100.0%
 flops    22 x    32 x    32         699349860352       0.0%      0.0%    100.0%
 flops     9 x    32 x     9        1735942275072       0.0%      0.0%    100.0%
 flops    22 x    32 x     9        2216407818240       0.0%      0.0%    100.0%
 flops     9 x    32 x    22        2216407818240       0.0%      0.0%    100.0%
 flops    22 x    32 x    22        2803661053952       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        12.884056E+12       0.0%      0.0%    100.0%
 flops max/rank                      1.612391E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                          984178160       0.0%      0.0%    100.0%
 number of processed stacks               1464624       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     672.0
 marketing flops                    15.646297E+12
 -------------------------------------------------------------------------------
 # multiplications                           2055
 max memory usage/rank               1.316532E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                   82200
 MPI messages size (bytes):
  total size                       297.640985E+09
  min size                           0.000000E+00
  max size                          26.214400E+06
  average size                       3.620936E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                 572                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                  44                  1441792
     32768 < size <=   131072               18560               2432696320
    131072 < size <=  4194304               54216              84915781632
   4194304 < size <= 16777216                   0                        0
  16777216 < size                            8808             210291069504
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             3462                  67104.
 MP_Allreduce         9672                    819.
 MP_Sync                52
 MP_Alltoall          1474               16505187.
 MP_SendRecv          2310                 360267.
 MP_ISendRecv         2310                 360267.
 MP_Wait              5214
 MP_ISend             2420                1187840.
 MP_IRecv             2420                1187840.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.023    0.050   86.139   86.139
 qs_mol_dyn_low                       1  2.0    0.003    0.003   85.716   85.724
 qs_forces                           11  3.9    0.002    0.002   85.652   85.653
 qs_energies                         11  4.9    0.001    0.001   81.569   81.570
 scf_env_do_scf                      11  5.9    0.001    0.001   71.491   71.491
 velocity_verlet                     10  3.0    0.002    0.002   55.130   55.136
 scf_env_do_scf_inner_loop           99  6.5    0.002    0.006   42.968   42.970
 dbcsr_multiply_generic            2055 12.4    0.120    0.122   28.662   28.858
 init_scf_loop                       11  6.9    0.000    0.000   28.451   28.455
 qs_scf_new_mos                      99  7.5    0.001    0.001   26.523   26.605
 qs_scf_loop_do_ot                   99  8.5    0.001    0.001   26.522   26.604
 prepare_preconditioner              11  7.9    0.000    0.000   26.516   26.527
 make_preconditioner                 11  8.9    0.000    0.000   26.516   26.527
 make_full_inverse_cholesky          11  9.9    0.000    0.000   20.827   25.996
 ot_scf_mini                         99  9.5    0.002    0.002   24.745   24.811
 multiply_cannon                   2055 13.4    0.343    0.375   21.447   21.992
 multiply_cannon_loop              2055 14.4    0.341    0.345   19.633   20.092
 cp_fm_upper_to_full                 70 14.2   12.677   18.090   12.677   18.090
 ot_mini                             99 10.5    0.001    0.001   13.736   13.809
 rebuild_ks_matrix                  110  8.3    0.001    0.001   13.168   13.261
 qs_ks_build_kohn_sham_matrix       110  9.3    0.013    0.013   13.168   13.260
 qs_ks_update_qs_env                110  7.6    0.001    0.001   11.974   12.057
 dbcsr_complete_redistribute        325 12.2    1.020    1.055    7.277   10.465
 multiply_cannon_multrec           8220 15.4    4.379    4.558    9.546    9.665
 copy_fm_to_dbcsr                   174 11.2    0.001    0.001    6.247    9.447
 qs_ot_get_derivative                99 11.5    0.001    0.001    9.139    9.204
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    5.674    8.845
 mp_alltoall_i22                    605 13.7    5.333    8.575    5.333    8.575
 mp_waitall_1                     84994 16.7    7.467    8.488    7.467    8.488
 sum_up_and_integrate               110 10.3    0.151    0.151    6.679    6.696
 integrate_v_rspace                 110 11.3    0.004    0.004    6.529    6.546
 qs_rho_update_rho_low              110  7.6    0.001    0.001    6.494    6.528
 calculate_rho_elec                 110  8.6    0.227    0.227    6.493    6.527
 qs_ot_get_p                        110 10.4    0.001    0.001    5.815    5.917
 init_scf_run                        11  5.9    0.000    0.001    5.817    5.817
 scf_env_initial_rho_setup           11  6.9    0.001    0.002    5.817    5.817
 make_m2s                          4110 13.4    0.045    0.045    5.313    5.812
 make_images                       4110 14.4    0.877    0.931    5.124    5.622
 cp_fm_cholesky_invert               11 10.9    5.562    5.566    5.562    5.566
 dbcsr_mm_accdrv_process          11614 15.7    3.208    3.664    5.024    5.289
 apply_preconditioner_dbcsr         110 12.6    0.000    0.000    4.624    5.165
 apply_single                       110 13.6    0.000    0.000    4.624    5.165
 multiply_cannon_metrocomm3        8220 15.4    0.018    0.019    4.693    5.062
 ot_diis_step                        99 11.5    0.015    0.016    4.566    4.566
 qs_ot_p2m_diag                      48 11.0    0.151    0.155    4.197    4.203
 multiply_cannon_sync_h2d          8220 15.4    3.951    3.956    3.951    3.956
 pw_transfer                       1331 11.6    0.074    0.075    3.785    3.788
 cp_dbcsr_syevd                      48 12.0    0.003    0.003    3.745    3.745
 grid_integrate_task_list           110 12.3    3.667    3.718    3.667    3.718
 fft_wrap_pw1pw2                   1111 12.6    0.009    0.009    3.668    3.672
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    3.645    3.645
 hybrid_alltoall_any               4261 16.3    0.255    0.551    2.922    3.592
 make_images_data                  4110 15.4    0.042    0.045    2.886    3.552
 qs_ot_get_derivative_taylor         52 13.0    0.001    0.001    2.890    3.352
 wfi_extrapolate                     11  7.9    0.001    0.001    3.224    3.224
 calculate_dm_sparse                110  9.5    0.001    0.001    3.163    3.191
 fft_wrap_pw1pw2_140                451 13.1    0.215    0.216    3.168    3.177
 cp_fm_diag_elpa                     48 13.0    0.000    0.000    3.136    3.136
 cp_fm_diag_elpa_base                48 14.0    2.608    2.796    3.134    3.134
 density_rs2pw                      110  9.6    0.004    0.004    2.980    2.998
 cp_dbcsr_sm_fm_multiply             37  9.5    0.001    0.001    2.901    2.903
 fft3d_ps                          1111 14.6    1.265    1.277    2.877    2.883
 grid_collocate_task_list           110  9.6    2.635    2.653    2.635    2.653
 qs_ot_get_derivative_diag           47 12.0    0.001    0.001    2.469    2.507
 calculate_first_density_matrix       1  7.0    0.000    0.000    2.491    2.491
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    2.378    2.415
 qs_env_update_s_mstruct             11  6.9    0.000    0.000    2.185    2.242
 rs_pw_transfer                     902 11.9    0.010    0.011    2.169    2.221
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    2.092    2.198
 mp_alltoall_d11v                  2046 13.8    2.057    2.108    2.057    2.108
 potential_pw2rs                    110 12.3    0.021    0.021    2.103    2.106
 cp_fm_cholesky_decompose            22 10.9    2.055    2.068    2.055    2.068
 qs_create_task_list                 11  7.9    0.001    0.001    1.903    1.948
 generate_qs_task_list               11  8.9    0.739    0.794    1.902    1.947
 copy_dbcsr_to_fm                   151 11.3    0.003    0.003    1.793    1.858
 qs_ks_update_qs_env_forces          11  4.9    0.000    0.000    1.799    1.808
 jit_kernel_multiply                 10 15.4    1.616    1.760    1.616    1.760
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="210", plot="h2o_128_md", label="(8n/1r/12t)", y=86.139000, yerr=0.000000
PlotPoint: name="211", plot="h2o_128_md_mem", label="(8n/1r/12t)", y=1200.909091, yerr=47.431203
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/15/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420242647040       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528903135232       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514766E+12       0.0%      0.0%    100.0%
 flops max/rank                      1.094965E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755941440       0.0%      0.0%    100.0%
 number of processed stacks              11950464       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0     565.3
 marketing flops                   144.580175E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank             628.580352E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                10348896
 MPI messages size (bytes):
  total size                         4.491514E+12
  min size                           0.000000E+00
  max size                           4.537280E+06
  average size                     434.009000E+03
 MPI breakdown and total messages size (bytes):
             size <=      128               65736                        0
       128 < size <=     8192                1232                 10092544
      8192 < size <=    32768             3576680              95640223744
     32768 < size <=   131072             1294784              74079797248
    131072 < size <=  4194304             5148576            3175955383376
   4194304 < size <= 16777216              261888            1145794321408
  16777216 < size                               0                        0
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4093                  56650.
 MP_Allreduce        11273                    784.
 MP_Sync               170
 MP_Alltoall          2226                3035554.
 MP_SendRecv         24320                  18752.
 MP_ISendRecv        24320                  18752.
 MP_Wait             42476
 MP_comm_split          83
 MP_ISend            16020                 108028.
 MP_IRecv            16020                 108028.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.013    0.030  205.291  205.292
 qs_mol_dyn_low                       1  2.0    0.003    0.003  204.836  204.849
 qs_forces                           11  3.9    0.003    0.003  204.737  204.739
 qs_energies                         11  4.9    0.001    0.001  199.200  199.218
 scf_env_do_scf                      11  5.9    0.001    0.001  182.222  182.225
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.008  160.885  160.887
 dbcsr_multiply_generic            2507 12.6    0.177    0.181  124.802  125.505
 velocity_verlet                     10  3.0    0.001    0.002  123.398  123.399
 qs_scf_new_mos                     117  7.6    0.001    0.001  121.914  122.239
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001  121.913  122.238
 ot_scf_mini                        117  9.6    0.003    0.003  115.282  115.575
 multiply_cannon                   2507 13.6    0.236    0.246  101.509  103.609
 multiply_cannon_loop              2507 14.6    2.119    2.187   99.218  101.142
 ot_mini                            117 10.6    0.001    0.001   65.724   66.018
 multiply_cannon_multrec          60168 15.6   33.221   35.404   41.957   44.417
 qs_ot_get_derivative               117 11.6    0.001    0.001   40.853   41.136
 rebuild_ks_matrix                  128  8.3    0.001    0.001   33.469   33.826
 qs_ks_build_kohn_sham_matrix       128  9.3    0.015    0.017   33.468   33.825
 mp_waitall_1                    267128 16.5   28.393   31.525   28.393   31.525
 qs_ks_update_qs_env                128  7.6    0.001    0.001   30.127   30.431
 multiply_cannon_sync_h2d         60168 15.6   27.302   29.135   27.302   29.135
 qs_ot_get_p                        128 10.4    0.001    0.001   27.592   27.988
 apply_preconditioner_dbcsr         128 12.6    0.000    0.001   24.324   25.297
 apply_single                       128 13.6    0.001    0.001   24.323   25.297
 ot_diis_step                       117 11.6    0.007    0.008   24.514   24.515
 init_scf_loop                       11  6.9    0.000    0.000   21.257   21.259
 qs_ot_p2m_diag                      83 11.4    0.077    0.092   20.828   20.900
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002   18.705   18.938
 multiply_cannon_metrocomm3       60168 15.6    0.115    0.120   15.679   18.418
 cp_dbcsr_syevd                      83 12.4    0.004    0.005   18.134   18.136
 prepare_preconditioner              11  7.9    0.000    0.000   16.655   16.693
 make_preconditioner                 11  8.9    0.000    0.000   16.655   16.693
 make_full_inverse_cholesky          11  9.9    0.000    0.000   15.858   16.031
 cp_fm_diag_elpa                     83 13.4    0.000    0.001   15.210   15.215
 cp_fm_redistribute_end              83 14.4   12.019   15.131   12.032   15.133
 cp_fm_diag_elpa_base                83 14.4    3.056   14.759    3.090   14.879
 make_m2s                          5014 13.6    0.106    0.113   13.841   14.124
 sum_up_and_integrate               128 10.3    0.089    0.107   14.075   14.093
 integrate_v_rspace                 128 11.3    0.003    0.004   13.986   14.006
 make_images                       5014 14.6    0.401    0.418   13.657   13.955
 qs_rho_update_rho_low              128  7.7    0.001    0.001   12.705   12.849
 calculate_rho_elec                 128  8.7    0.045    0.063   12.705   12.848
 init_scf_run                        11  5.9    0.000    0.001   12.820   12.821
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   12.820   12.821
 mp_sum_l                          7870 13.0    8.184    9.819    8.184    9.819
 cp_fm_cholesky_invert               11 10.9    9.571    9.580    9.571    9.580
 wfi_extrapolate                     11  7.9    0.001    0.001    9.145    9.145
 dbcsr_mm_accdrv_process         124484 16.2    3.292    3.449    8.299    8.860
 calculate_dm_sparse                128  9.5    0.001    0.001    8.600    8.674
 multiply_cannon_metrocomm1       60168 15.6    0.087    0.091    6.106    8.595
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    8.082    8.228
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    7.824    7.914
 make_images_data                  5014 15.6    0.066    0.071    6.761    7.727
 grid_integrate_task_list           128 12.3    7.075    7.495    7.075    7.495
 hybrid_alltoall_any               5200 16.5    0.290    2.261    5.903    7.189
 pw_transfer                       1547 11.6    0.075    0.108    6.905    7.183
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.003    6.989    6.997
 density_rs2pw                      128  9.7    0.006    0.007    6.527    6.957
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.013    6.701    6.949
 rs_pw_transfer                    1046 11.9    0.016    0.019    5.748    6.266
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    6.111    6.231
 fft_wrap_pw1pw2_140                523 13.2    0.445    0.508    5.759    5.930
 fft3d_ps                          1291 14.7    2.092    2.567    5.492    5.687
 mp_alltoall_d11v                  2415 14.1    4.299    5.568    4.299    5.568
 grid_collocate_task_list           128  9.7    4.725    5.064    4.725    5.064
 cp_fm_cholesky_decompose            22 10.9    4.849    4.865    4.849    4.865
 potential_pw2rs                    128 12.3    0.009    0.010    4.530    4.559
 mp_sum_d                          4464 12.2    3.600    4.322    3.600    4.322
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="400", plot="h2o_256_md", label="(8n/12r/1t)", y=205.292000, yerr=0.000000
PlotPoint: name="401", plot="h2o_256_md_mem", label="(8n/12r/1t)", y=595.727273, yerr=7.249964
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/16/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1410022950912       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1924145348608       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1957871443968       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1963542011904       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2714615709696       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4377645416448       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5350455508992       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5395653328896       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6594687401984       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11444706349056       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15019182452736       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15019182452736       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19624853225472       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        92.796564E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.166473E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6705499488       0.0%      0.0%    100.0%
 number of processed stacks               5925696       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1131.6
 marketing flops                   143.508480E+12
 -------------------------------------------------------------------------------
 # multiplications                           2485
 max memory usage/rank             829.231104E+06
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 2385600
 MPI messages size (bytes):
  total size                         4.069299E+12
  min size                           0.000000E+00
  max size                          17.653760E+06
  average size                       1.705776E+06
 MPI breakdown and total messages size (bytes):
             size <=      128               14916                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768               70188               2295595008
     32768 < size <=   131072              716032              54973693952
    131072 < size <=  4194304             1363760            1386318135296
   4194304 < size <= 16777216              153648            1453842592400
  16777216 < size                           67056            1171888537600
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4077                  57311.
 MP_Allreduce        11232                    947.
 MP_Sync               168
 MP_Alltoall          1955                5106737.
 MP_SendRecv         11938                  47072.
 MP_ISendRecv        11938                  47072.
 MP_Wait             25718
 MP_comm_split          82
 MP_ISend            11660                 212488.
 MP_IRecv            11660                 212488.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.021    0.038  189.999  190.001
 qs_mol_dyn_low                       1  2.0    0.003    0.004  189.520  189.533
 qs_forces                           11  3.9    0.013    0.022  189.437  189.438
 qs_energies                         11  4.9    0.003    0.012  182.699  182.717
 scf_env_do_scf                      11  5.9    0.001    0.001  166.324  166.334
 scf_env_do_scf_inner_loop          116  6.6    0.003    0.009  132.839  132.841
 velocity_verlet                     10  3.0    0.001    0.003  118.922  118.924
 dbcsr_multiply_generic            2485 12.5    0.184    0.190   96.879   98.033
 qs_scf_new_mos                     116  7.6    0.001    0.001   94.665   95.171
 qs_scf_loop_do_ot                  116  8.6    0.001    0.001   94.664   95.170
 ot_scf_mini                        116  9.6    0.004    0.005   89.855   90.404
 multiply_cannon                   2485 13.5    0.476    0.527   77.107   81.004
 multiply_cannon_loop              2485 14.5    1.247    1.286   73.612   76.096
 ot_mini                            116 10.6    0.001    0.001   49.475   49.954
 mp_waitall_1                    212858 16.6   24.113   38.329   24.113   38.329
 multiply_cannon_multrec          29820 15.5   21.993   27.149   31.538   37.111
 init_scf_loop                       11  6.9    0.001    0.002   33.393   33.394
 rebuild_ks_matrix                  127  8.3    0.001    0.001   32.512   32.964
 qs_ks_build_kohn_sham_matrix       127  9.3    0.016    0.019   32.512   32.963
 qs_ks_update_qs_env                127  7.6    0.001    0.001   29.290   29.716
 prepare_preconditioner              11  7.9    0.000    0.000   28.986   29.048
 make_preconditioner                 11  8.9    0.000    0.001   28.986   29.048
 make_full_inverse_cholesky          11  9.9    0.000    0.000   27.653   28.183
 qs_ot_get_derivative               116 11.6    0.001    0.002   27.636   28.172
 multiply_cannon_metrocomm3       29820 15.5    0.093    0.097   15.422   28.117
 apply_preconditioner_dbcsr         127 12.6    0.000    0.000   21.939   22.992
 apply_single                       127 13.6    0.001    0.001   21.939   22.991
 qs_ot_get_p                        127 10.4    0.001    0.001   22.186   22.767
 ot_diis_step                       116 11.6    0.014    0.015   21.661   21.663
 multiply_cannon_sync_h2d         29820 15.5   19.300   21.184   19.300   21.184
 qs_ot_p2m_diag                      82 11.4    0.185    0.214   17.461   17.500
 cp_fm_cholesky_invert               11 10.9   16.963   16.976   16.963   16.976
 cp_dbcsr_syevd                      82 12.4    0.005    0.005   16.309   16.310
 make_m2s                          4970 13.5    0.091    0.097   14.120   15.821
 make_images                       4970 14.5    1.138    1.325   13.908   15.606
 sum_up_and_integrate               127 10.3    0.115    0.132   14.195   14.228
 integrate_v_rspace                 127 11.3    0.003    0.003   14.080   14.115
 cp_fm_diag_elpa                     82 13.4    0.000    0.001   13.145   13.158
 cp_fm_redistribute_end              82 14.4    7.674   13.077    7.684   13.078
 cp_fm_diag_elpa_base                82 14.4    5.152   12.567    5.371   12.930
 qs_rho_update_rho_low              127  7.7    0.001    0.001   12.754   12.788
 calculate_rho_elec                 127  8.7    0.087    0.104   12.753   12.787
 init_scf_run                        11  5.9    0.000    0.001   11.516   11.518
 scf_env_initial_rho_setup           11  6.9    0.001    0.002   11.516   11.517
 qs_ot_get_derivative_diag           76 12.4    0.002    0.002   10.853   11.241
 make_images_data                  4970 15.5    0.064    0.071    8.536   10.508
 multiply_cannon_metrocomm4       27335 15.5    0.093    0.107    3.665   10.356
 hybrid_alltoall_any               5155 16.4    0.339    1.497    7.300   10.064
 mp_irecv_dv                      68888 16.3    3.475    9.976    3.475    9.976
 dbcsr_mm_accdrv_process          61726 16.2    4.549    5.423    9.007    9.587
 wfi_extrapolate                     11  7.9    0.001    0.001    8.432    8.432
 pw_transfer                       1535 11.6    0.084    0.103    7.677    7.751
 fft_wrap_pw1pw2                   1281 12.7    0.010    0.011    7.455    7.514
 grid_integrate_task_list           127 12.3    7.101    7.426    7.101    7.426
 cp_fm_cholesky_decompose            22 10.9    7.137    7.214    7.137    7.214
 density_rs2pw                      127  9.7    0.006    0.006    6.628    7.054
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    6.159    6.959
 calculate_dm_sparse                127  9.5    0.001    0.002    6.461    6.608
 fft_wrap_pw1pw2_140                519 13.2    0.465    0.516    6.467    6.527
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.142    6.151
 rs_pw_transfer                    1038 11.9    0.014    0.016    5.553    5.985
 mp_sum_l                          7804 13.0    3.900    5.891    3.900    5.891
 fft3d_ps                          1281 14.7    2.753    2.903    5.840    5.872
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    5.299    5.433
 qs_ot_get_orbitals                 116 10.6    0.001    0.001    5.319    5.393
 grid_collocate_task_list           127  9.7    4.873    5.242    4.873    5.242
 mp_allgather_i34                  2485 14.5    2.080    5.116    2.080    5.116
 potential_pw2rs                    127 12.3    0.015    0.018    4.781    4.801
 mp_alltoall_d11v                  2401 14.1    4.087    4.480    4.087    4.480
 dbcsr_complete_redistribute        393 12.7    0.766    0.846    3.173    4.039
 mp_sum_d                          4438 12.1    2.661    4.026    2.661    4.026
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="402", plot="h2o_256_md", label="(8n/6r/2t)", y=190.001000, yerr=0.000000
PlotPoint: name="403", plot="h2o_256_md_mem", label="(8n/6r/2t)", y=790.090909, yerr=2.874798
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/17/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1430460020736       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1958505086976       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1986244964352       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1992000282624       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2753956716544       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4454954827776       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5444944789504       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5492290093056       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6712799002624       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11613089636352       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15239146475520       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15239146475520       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19911124992000       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        94.228663E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.950886E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6806316384       0.0%      0.0%    100.0%
 number of processed stacks               4015680       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1694.9
 marketing flops                   145.646636E+12
 -------------------------------------------------------------------------------
 # multiplications                           2527
 max memory usage/rank             939.491328E+06
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                 1051232
 MPI messages size (bytes):
  total size                         2.737039E+12
  min size                           0.000000E+00
  max size                          26.214400E+06
  average size                       2.603648E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                6424                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 264                  8650752
     32768 < size <=   131072              284160              37245419520
    131072 < size <=  4194304              665408            1004401590272
   4194304 < size <= 16777216               66080             937889764224
  16777216 < size                           28896             757491302400
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4107                  56898.
 MP_Allreduce        11306                    983.
 MP_Sync               170
 MP_Alltoall          1724                9394172.
 MP_SendRecv          7998                  75008.
 MP_ISendRecv         7998                  75008.
 MP_Wait             21986
 MP_comm_split          83
 MP_ISend            11836                 275177.
 MP_IRecv            11836                 275177.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.054    0.129  178.145  178.147
 qs_mol_dyn_low                       1  2.0    0.003    0.012  177.585  177.597
 qs_forces                           11  3.9    0.022    0.028  177.368  177.376
 qs_energies                         11  4.9    0.006    0.027  170.783  170.796
 scf_env_do_scf                      11  5.9    0.007    0.024  155.308  155.312
 scf_env_do_scf_inner_loop          118  6.6    0.007    0.023  119.613  119.616
 velocity_verlet                     10  3.0    0.004    0.023  114.207  114.213
 dbcsr_multiply_generic            2527 12.6    0.183    0.186   82.276   83.231
 qs_scf_new_mos                     118  7.6    0.001    0.001   82.815   83.145
 qs_scf_loop_do_ot                  118  8.6    0.001    0.001   82.814   83.144
 ot_scf_mini                        118  9.6    0.005    0.011   78.629   79.000
 multiply_cannon                   2527 13.6    0.507    0.539   62.292   66.648
 multiply_cannon_loop              2527 14.6    0.863    0.890   58.982   61.245
 ot_mini                            118 10.6    0.001    0.001   43.158   43.531
 init_scf_loop                       11  6.9    0.001    0.004   35.573   35.579
 mp_waitall_1                    171878 16.6   25.196   34.659   25.196   34.659
 prepare_preconditioner              11  7.9    0.000    0.000   31.537   31.591
 make_preconditioner                 11  8.9    0.000    0.003   31.537   31.591
 rebuild_ks_matrix                  129  8.3    0.001    0.001   30.224   30.692
 qs_ks_build_kohn_sham_matrix       129  9.3    0.016    0.019   30.224   30.692
 make_full_inverse_cholesky          11  9.9    0.000    0.000   29.194   30.629
 qs_ks_update_qs_env                129  7.6    0.001    0.001   27.242   27.674
 multiply_cannon_multrec          20216 15.6   13.565   16.594   22.231   25.174
 multiply_cannon_metrocomm3       20216 15.6    0.060    0.064   15.388   24.889
 qs_ot_get_derivative               118 11.6    0.001    0.002   23.151   23.529
 qs_ot_get_p                        129 10.4    0.007    0.025   20.818   21.257
 apply_preconditioner_dbcsr         129 12.6    0.000    0.000   20.099   21.080
 apply_single                       129 13.6    0.001    0.001   20.098   21.079
 ot_diis_step                       118 11.6    0.018    0.018   19.903   19.904
 qs_ot_p2m_diag                      83 11.4    0.266    0.272   16.431   16.441
 multiply_cannon_sync_h2d         20216 15.6   14.334   15.886   14.334   15.886
 make_m2s                          5054 13.6    0.084    0.090   14.818   15.710
 make_images                       5054 14.6    1.193    1.322   14.581   15.472
 cp_dbcsr_syevd                      83 12.4    0.005    0.005   15.391   15.392
 cp_fm_cholesky_invert               11 10.9   14.808   14.818   14.808   14.818
 sum_up_and_integrate               129 10.3    0.134    0.145   14.262   14.313
 integrate_v_rspace                 129 11.3    0.003    0.004   14.128   14.182
 qs_rho_update_rho_low              129  7.7    0.001    0.001   13.160   13.202
 calculate_rho_elec                 129  8.7    0.133    0.148   13.159   13.201
 cp_fm_diag_elpa                     83 13.4    0.000    0.001   12.149   12.151
 cp_fm_redistribute_end              83 14.4    4.591   12.066    4.609   12.070
 cp_fm_diag_elpa_base                83 14.4    7.021   11.444    7.439   11.929
 init_scf_run                        11  5.9    0.000    0.001   10.412   10.413
 scf_env_initial_rho_setup           11  6.9    0.001    0.002   10.412   10.412
 make_images_data                  5054 15.6    0.061    0.069    9.075   10.322
 hybrid_alltoall_any               5240 16.5    0.433    1.991    7.948    9.582
 qs_ot_get_derivative_diag           77 12.4    0.002    0.003    9.051    9.307
 multiply_cannon_metrocomm4       17689 15.6    0.062    0.072    3.490    9.297
 mp_irecv_dv                      50625 16.2    3.367    9.044    3.367    9.044
 dbcsr_mm_accdrv_process          41830 16.2    4.333    5.246    8.125    8.291
 pw_transfer                       1559 11.6    0.086    0.106    7.855    7.985
 grid_integrate_task_list           129 12.3    7.359    7.891    7.359    7.891
 fft_wrap_pw1pw2                   1301 12.7    0.010    0.012    7.630    7.763
 cp_fm_cholesky_decompose            22 10.9    7.519    7.555    7.519    7.555
 cp_fm_upper_to_full                105 14.5    5.842    7.540    5.842    7.540
 wfi_extrapolate                     11  7.9    0.001    0.001    7.409    7.409
 density_rs2pw                      129  9.7    0.006    0.006    6.591    7.085
 fft_wrap_pw1pw2_140                527 13.2    0.481    0.534    6.696    6.841
 dbcsr_complete_redistribute        395 12.7    1.172    1.198    4.609    6.378
 fft3d_ps                          1301 14.7    2.712    2.918    5.888    5.978
 calculate_dm_sparse                129  9.5    0.001    0.002    5.776    5.878
 rs_pw_transfer                    1054 12.0    0.014    0.014    5.123    5.580
 grid_collocate_task_list           129  9.7    5.112    5.510    5.112    5.510
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.440    5.445
 qs_ot_get_derivative_taylor         41 13.0    0.001    0.001    4.692    5.360
 copy_fm_to_dbcsr                   209 11.7    0.002    0.002    3.433    5.199
 mp_alltoall_d11v                  2423 14.1    4.261    4.811    4.261    4.811
 mp_sum_l                          7930 13.1    3.375    4.796    3.375    4.796
 mp_allgather_i34                  2527 14.6    1.825    4.690    1.825    4.690
 potential_pw2rs                    129 12.3    0.020    0.022    4.579    4.627
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.507    4.626
 qs_ot_get_orbitals                 118 10.6    0.001    0.001    4.101    4.142
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    2.323    4.063
 mp_alltoall_i22                    718 14.1    1.970    3.880    1.970    3.880
 qs_energies_init_hamiltonians       11  5.9    0.005    0.019    3.731    3.740
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="404", plot="h2o_256_md", label="(8n/4r/3t)", y=178.147000, yerr=0.000000
PlotPoint: name="405", plot="h2o_256_md_mem", label="(8n/4r/3t)", y=888.636364, yerr=10.890135
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/18/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420239992832       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528891191296       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514751E+12       0.0%      0.0%    100.0%
 flops max/rank                      4.353788E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755938624       0.0%      0.0%    100.0%
 number of processed stacks               5977344       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    1130.3
 marketing flops                   144.580175E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank               1.151517E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                 1143192
 MPI messages size (bytes):
  total size                         2.023815E+12
  min size                           0.000000E+00
  max size                          17.653760E+06
  average size                       1.770319E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                6996                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 396                  8650752
     32768 < size <=   131072              319024              36042702848
    131072 < size <=  4194304              715736             785529176064
   4194304 < size <= 16777216               70320             665379241840
  16777216 < size                           30720             536870912000
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4075                  57332.
 MP_Allreduce        11226                   1068.
 MP_Sync               170
 MP_Alltoall          1712               12503084.
 MP_SendRecv          5888                  75008.
 MP_ISendRecv         5888                  75008.
 MP_Wait             22442
 MP_comm_split          83
 MP_ISend            14952                 244818.
 MP_IRecv            14952                 244818.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.034    0.056  190.329  190.331
 qs_mol_dyn_low                       1  2.0    0.003    0.004  189.786  189.798
 qs_forces                           11  3.9    0.003    0.005  189.672  189.678
 qs_energies                         11  4.9    0.003    0.010  182.587  182.597
 scf_env_do_scf                      11  5.9    0.001    0.002  165.746  165.756
 velocity_verlet                     10  3.0    0.002    0.002  126.086  126.089
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.009  118.145  118.147
 qs_scf_new_mos                     117  7.6    0.001    0.001   82.039   82.400
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   82.038   82.399
 dbcsr_multiply_generic            2507 12.6    0.189    0.192   80.113   80.880
 ot_scf_mini                        117  9.6    0.004    0.004   77.510   77.825
 multiply_cannon                   2507 13.6    0.555    0.592   55.147   58.090
 multiply_cannon_loop              2507 14.6    1.186    1.217   50.985   52.793
 init_scf_loop                       11  6.9    0.001    0.002   47.475   47.479
 prepare_preconditioner              11  7.9    0.000    0.000   43.374   43.407
 make_preconditioner                 11  8.9    0.000    0.001   43.373   43.407
 ot_mini                            117 10.6    0.001    0.001   42.906   43.226
 make_full_inverse_cholesky          11  9.9    0.000    0.000   36.984   41.923
 multiply_cannon_multrec          30084 15.6   13.951   19.396   25.837   30.736
 rebuild_ks_matrix                  128  8.3    0.001    0.001   29.375   29.633
 qs_ks_build_kohn_sham_matrix       128  9.3    0.016    0.018   29.375   29.632
 mp_waitall_1                    147882 16.7   17.783   28.608   17.783   28.608
 qs_ks_update_qs_env                128  7.6    0.001    0.001   26.545   26.775
 qs_ot_get_derivative               117 11.6    0.001    0.002   23.189   23.513
 make_m2s                          5014 13.6    0.098    0.104   20.384   21.620
 make_images                       5014 14.6    1.928    2.249   20.073   21.309
 qs_ot_get_p                        128 10.4    0.001    0.001   20.745   21.072
 apply_preconditioner_dbcsr         128 12.6    0.000    0.001   19.053   19.686
 apply_single                       128 13.6    0.001    0.001   19.053   19.686
 ot_diis_step                       117 11.6    0.017    0.018   19.586   19.588
 cp_fm_cholesky_invert               11 10.9   17.020   17.028   17.020   17.028
 qs_ot_p2m_diag                      83 11.4    0.343    0.390   16.400   16.457
 cp_fm_upper_to_full                105 14.7   11.010   16.283   11.010   16.283
 multiply_cannon_metrocomm3       30084 15.6    0.047    0.049    6.576   15.599
 cp_dbcsr_syevd                      83 12.4    0.005    0.005   15.066   15.067
 sum_up_and_integrate               128 10.3    0.140    0.151   14.316   14.344
 integrate_v_rspace                 128 11.3    0.003    0.003   14.176   14.209
 qs_rho_update_rho_low              128  7.7    0.001    0.001   13.406   13.447
 calculate_rho_elec                 128  8.7    0.175    0.190   13.405   13.446
 dbcsr_complete_redistribute        395 12.7    1.497    1.617    9.119   12.890
 make_images_data                  5014 15.6    0.064    0.068   10.987   12.766
 multiply_cannon_sync_h2d         30084 15.6   11.692   12.597   11.692   12.597
 dbcsr_mm_accdrv_process          62264 16.2    7.309    8.105   11.466   11.976
 hybrid_alltoall_any               5200 16.5    0.513    2.069    9.885   11.970
 cp_fm_diag_elpa                     83 13.4    0.000    0.001   11.804   11.807
 cp_fm_redistribute_end              83 14.4    2.051   11.712    2.071   11.717
 cp_fm_diag_elpa_base                83 14.4    9.016   11.045    9.607   11.546
 copy_fm_to_dbcsr                   209 11.7    0.002    0.002    7.662   11.344
 init_scf_run                        11  5.9    0.000    0.001   10.893   10.895
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   10.892   10.895
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000    6.367    9.920
 qs_ot_get_derivative_diag           77 12.4    0.002    0.002    9.632    9.862
 mp_alltoall_i22                    716 14.1    5.540    9.175    5.540    9.175
 pw_transfer                       1547 11.6    0.085    0.100    8.168    8.269
 fft_wrap_pw1pw2                   1291 12.7    0.010    0.011    7.943    8.045
 cp_fm_cholesky_decompose            22 10.9    7.872    7.961    7.872    7.961
 grid_integrate_task_list           128 12.3    7.524    7.851    7.524    7.851
 wfi_extrapolate                     11  7.9    0.001    0.001    7.763    7.764
 fft_wrap_pw1pw2_140                523 13.2    0.481    0.487    6.979    7.108
 multiply_cannon_metrocomm4       25070 15.6    0.076    0.086    2.832    6.795
 density_rs2pw                      128  9.7    0.006    0.006    6.496    6.743
 mp_irecv_dv                      76098 16.2    2.687    6.537    2.687    6.537
 calculate_dm_sparse                128  9.5    0.001    0.002    6.227    6.308
 fft3d_ps                          1291 14.7    2.800    2.904    6.173    6.236
 mp_alltoall_d11v                  2415 14.1    5.087    6.038    5.087    6.038
 grid_collocate_task_list           128  9.7    5.212    5.542    5.212    5.542
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.471    5.508
 rs_pw_transfer                    1046 11.9    0.013    0.014    4.814    5.090
 qs_ot_get_derivative_taylor         40 13.0    0.001    0.001    4.457    4.550
 potential_pw2rs                    128 12.3    0.022    0.023    4.483    4.512
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.354    4.444
 qs_energies_init_hamiltonians       11  5.9    0.001    0.002    4.434    4.435
 qs_ot_get_orbitals                 117 10.6    0.001    0.001    4.266    4.327
 mp_allgather_i34                  2507 14.6    2.274    3.820    2.274    3.820
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="406", plot="h2o_256_md", label="(8n/3r/4t)", y=190.331000, yerr=0.000000
PlotPoint: name="407", plot="h2o_256_md_mem", label="(8n/3r/4t)", y=1085.272727, yerr=18.844295
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/19/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1430460020736       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1958505086976       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1986244964352       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1992000282624       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2753956716544       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4454954827776       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5444944789504       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5492290093056       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6712799002624       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11613089636352       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15239146475520       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15239146475520       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19911124992000       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        94.228663E+12       0.0%      0.0%    100.0%
 flops max/rank                      5.909858E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6806316384       0.0%      0.0%    100.0%
 number of processed stacks               1976192       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    3444.2
 marketing flops                   145.646636E+12
 -------------------------------------------------------------------------------
 # multiplications                           2527
 max memory usage/rank               1.523454E+09
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                  242592
 MPI messages size (bytes):
  total size                         1.341705E+12
  min size                           0.000000E+00
  max size                          52.428800E+06
  average size                       5.530704E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                1452                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                 132                  8650752
    131072 < size <=  4194304              114816              60196651008
   4194304 < size <= 16777216              105840             554906419200
  16777216 < size                           20352             726591885696
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast               14                     12.
 MP_Allreduce         9003                     51.
 MP_Alltoall          9708                 795382.
 MP_ISend            40388                2101966.
 MP_IRecv            40388                2101070.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4024                  57898.
 MP_Allreduce        11057                   1172.
 MP_Sync                87
 MP_Alltoall          1724               18848418.
 MP_SendRecv          3870                 122880.
 MP_ISendRecv         3870                 122880.
 MP_Wait             16244
 MP_ISend            10760                 423501.
 MP_IRecv            10760                 423501.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.017    0.034  178.542  178.543
 qs_mol_dyn_low                       1  2.0    0.003    0.004  178.114  178.126
 qs_forces                           11  3.9    0.003    0.003  177.953  177.956
 qs_energies                         11  4.9    0.001    0.001  170.511  170.520
 scf_env_do_scf                      11  5.9    0.001    0.001  153.133  153.143
 velocity_verlet                     10  3.0    0.033    0.038  117.334  117.341
 scf_env_do_scf_inner_loop          118  6.6    0.003    0.008  115.736  115.738
 qs_scf_new_mos                     118  7.6    0.001    0.001   79.159   79.241
 qs_scf_loop_do_ot                  118  8.6    0.001    0.001   79.158   79.240
 dbcsr_multiply_generic            2527 12.6    0.184    0.189   76.661   77.162
 ot_scf_mini                        118  9.6    0.004    0.004   74.643   74.732
 multiply_cannon                   2527 13.6    0.592    0.630   55.784   60.330
 multiply_cannon_loop              2527 14.6    0.449    0.459   50.694   51.667
 ot_mini                            118 10.6    0.001    0.001   41.050   41.140
 init_scf_loop                       11  6.9    0.000    0.000   37.229   37.232
 mp_waitall_1                    126780 16.7   27.349   35.392   27.349   35.392
 prepare_preconditioner              11  7.9    0.000    0.000   33.325   33.353
 make_preconditioner                 11  8.9    0.000    0.000   33.325   33.353
 make_full_inverse_cholesky          11  9.9    0.000    0.000   31.211   31.475
 rebuild_ks_matrix                  129  8.3    0.001    0.001   29.183   29.280
 qs_ks_build_kohn_sham_matrix       129  9.3    0.017    0.018   29.183   29.279
 qs_ks_update_qs_env                129  7.6    0.001    0.001   26.620   26.716
 multiply_cannon_multrec          10108 15.6   10.513   14.741   17.810   21.540
 qs_ot_get_derivative               118 11.6    0.001    0.002   20.578   20.673
 ot_diis_step                       118 11.6    0.020    0.020   20.383   20.385
 qs_ot_get_p                        129 10.4    0.001    0.001   20.214   20.308
 apply_preconditioner_dbcsr         129 12.6    0.000    0.000   19.918   20.262
 apply_single                       129 13.6    0.001    0.001   19.917   20.262
 multiply_cannon_metrocomm3       10108 15.6    0.023    0.024   12.777   19.818
 make_m2s                          5054 13.6    0.069    0.074   16.976   19.797
 make_images                       5054 14.6    2.349    2.878   16.665   19.493
 cp_fm_cholesky_invert               11 10.9   19.294   19.301   19.294   19.301
 qs_ot_p2m_diag                      83 11.4    0.496    0.503   16.045   16.059
 cp_dbcsr_syevd                      83 12.4    0.005    0.005   14.868   14.870
 sum_up_and_integrate               129 10.3    0.183    0.193   14.401   14.447
 integrate_v_rspace                 129 11.3    0.003    0.004   14.218   14.275
 qs_rho_update_rho_low              129  7.7    0.001    0.001   13.610   13.645
 calculate_rho_elec                 129  8.7    0.260    0.271   13.609   13.644
 make_images_data                  5054 15.6    0.053    0.060   10.393   13.433
 hybrid_alltoall_any               5240 16.5    0.820    3.604   10.123   12.738
 multiply_cannon_sync_h2d         10108 15.6   11.638   12.661   11.638   12.661
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   11.605   11.615
 cp_fm_diag_elpa_base                83 14.4   11.340   11.440   11.593   11.604
 init_scf_run                        11  5.9    0.000    0.001   10.513   10.513
 scf_env_initial_rho_setup           11  6.9    0.001    0.001   10.513   10.513
 cp_fm_cholesky_decompose            22 10.9    8.345    8.458    8.345    8.458
 qs_ot_get_derivative_diag           77 12.4    0.002    0.003    8.367    8.439
 multiply_cannon_metrocomm1       10108 15.6    0.029    0.029    4.836    8.264
 grid_integrate_task_list           129 12.3    7.815    8.149    7.815    8.149
 pw_transfer                       1559 11.6    0.085    0.092    8.122    8.140
 mp_allgather_i34                  2527 14.6    3.286    8.080    3.286    8.080
 fft_wrap_pw1pw2                   1301 12.7    0.010    0.010    7.899    7.923
 wfi_extrapolate                     11  7.9    0.001    0.001    7.585    7.585
 dbcsr_mm_accdrv_process          20926 16.1    2.650    3.466    6.926    7.549
 fft_wrap_pw1pw2_140                527 13.2    0.504    0.526    6.838    6.868
 density_rs2pw                      129  9.7    0.005    0.006    6.275    6.554
 calculate_dm_sparse                129  9.5    0.001    0.001    6.175    6.252
 fft3d_ps                          1301 14.7    2.742    2.819    6.052    6.088
 grid_collocate_task_list           129  9.7    5.530    5.879    5.530    5.879
 dbcsr_complete_redistribute        395 12.7    2.122    2.184    5.327    5.590
 mp_alltoall_d11v                  2423 14.1    5.001    5.538    5.001    5.538
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    5.341    5.366
 qs_energies_init_hamiltonians       11  5.9    0.000    0.001    5.269    5.271
 rs_pw_transfer                    1054 12.0    0.013    0.013    4.383    4.674
 multiply_cannon_metrocomm4        7581 15.6    0.024    0.027    1.878    4.507
 mp_irecv_dv                      29086 15.9    1.841    4.427    1.841    4.427
 potential_pw2rs                    129 12.3    0.026    0.027    4.306    4.323
 cp_dbcsr_sm_fm_multiply_core        37 10.5    0.000    0.000    4.221    4.247
 qs_ot_get_orbitals                 118 10.6    0.001    0.001    3.851    3.888
 build_core_hamiltonian_matrix_      11  4.9    0.001    0.001    3.555    3.869
 copy_fm_to_dbcsr                   209 11.7    0.002    0.002    3.454    3.762
 copy_dbcsr_to_fm                   186 11.8    0.004    0.004    3.648    3.730
 qs_ot_get_derivative_taylor         41 13.0    0.001    0.001    3.655    3.683
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="408", plot="h2o_256_md", label="(8n/2r/6t)", y=178.543000, yerr=0.000000
PlotPoint: name="409", plot="h2o_256_md_mem", label="(8n/2r/6t)", y=1423.090909, yerr=45.830626
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/20/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops     9 x     9 x    32        1420242647040       0.0%      0.0%    100.0%
 flops    32 x    32 x    32        1943472701440       0.0%      0.0%    100.0%
 flops    22 x     9 x    32        1972057190400       0.0%      0.0%    100.0%
 flops     9 x    22 x    32        1977770336256       0.0%      0.0%    100.0%
 flops    22 x    22 x    32        2734287699968       0.0%      0.0%    100.0%
 flops    32 x    32 x     9        4416300122112       0.0%      0.0%    100.0%
 flops    32 x    32 x    22        5397700149248       0.0%      0.0%    100.0%
 flops     9 x    32 x    32        5443971710976       0.0%      0.0%    100.0%
 flops    22 x    32 x    32        6653743202304       0.0%      0.0%    100.0%
 flops     9 x    32 x     9       11528903135232       0.0%      0.0%    100.0%
 flops    22 x    32 x     9       15129160814592       0.0%      0.0%    100.0%
 flops     9 x    32 x    22       15129160814592       0.0%      0.0%    100.0%
 flops    22 x    32 x    22       19767995056128       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                        93.514766E+12       0.0%      0.0%    100.0%
 flops max/rank                     11.696234E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         6755941440       0.0%      0.0%    100.0%
 number of processed stacks               1964048       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0    3439.8
 marketing flops                   144.579337E+12
 -------------------------------------------------------------------------------
 # multiplications                           2507
 max memory usage/rank               2.993664E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                  100280
 MPI messages size (bytes):
  total size                         1.136195E+12
  min size                           0.000000E+00
  max size                         104.857600E+06
  average size                      11.330227E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                 572                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                  44                  2883584
    131072 < size <=  4194304               45208              35089547264
   4194304 < size <= 16777216               44352             379752284160
  16777216 < size                           10104             721350232272
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             4002                  59142.
 MP_Allreduce        11002                   1514.
 MP_Sync                87
 MP_Alltoall          1712               36974159.
 MP_SendRecv          1792                 218624.
 MP_ISendRecv         1792                 218624.
 MP_Wait              9802
 MP_ISend             6408                1080322.
 MP_IRecv             6408                1080322.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.069    0.086  289.169  289.169
 qs_mol_dyn_low                       1  2.0    0.003    0.003  288.608  288.619
 qs_forces                           11  3.9    0.003    0.004  288.511  288.515
 qs_energies                         11  4.9    0.001    0.001  279.885  279.899
 scf_env_do_scf                      11  5.9    0.001    0.001  257.887  257.900
 velocity_verlet                     10  3.0    0.008    0.009  209.064  209.072
 scf_env_do_scf_inner_loop          117  6.6    0.003    0.008  133.407  133.409
 init_scf_loop                       11  6.9    0.000    0.000  124.220  124.223
 prepare_preconditioner              11  7.9    0.000    0.000  119.463  119.494
 make_preconditioner                 11  8.9    0.000    0.000  119.463  119.494
 make_full_inverse_cholesky          11  9.9    0.000    0.000   96.056  116.639
 qs_scf_new_mos                     117  7.6    0.001    0.001   91.420   91.531
 qs_scf_loop_do_ot                  117  8.6    0.001    0.001   91.419   91.530
 ot_scf_mini                        117  9.6    0.004    0.004   86.641   86.670
 dbcsr_multiply_generic            2507 12.6    0.213    0.222   83.514   84.043
 cp_fm_upper_to_full                105 14.8   52.615   74.972   52.615   74.972
 multiply_cannon                   2507 13.6    0.702    0.733   58.838   59.402
 multiply_cannon_loop              2507 14.6    0.472    0.482   55.354   56.666
 ot_mini                            117 10.6    0.001    0.001   44.885   44.915
 dbcsr_complete_redistribute        395 12.7    3.978    4.017   29.113   41.687
 copy_fm_to_dbcsr                   209 11.7    0.002    0.002   25.697   38.204
 transfer_fm_to_dbcsr                11  9.9    0.000    0.000   23.361   35.717
 cp_fm_cholesky_invert               11 10.9   34.098   34.105   34.098   34.105
 mp_alltoall_i22                    716 14.1   21.167   33.863   21.167   33.863
 rebuild_ks_matrix                  128  8.3    0.001    0.001   33.488   33.530
 qs_ks_build_kohn_sham_matrix       128  9.3    0.017    0.017   33.487   33.530
 mp_waitall_1                    103674 16.8   28.707   32.375   28.707   32.375
 qs_ks_update_qs_env                128  7.6    0.001    0.001   31.204   31.246
 qs_ot_get_p                        128 10.4    0.001    0.001   26.286   26.358
 qs_ot_get_derivative               117 11.6    0.002    0.002   24.687   24.717
 qs_ot_p2m_diag                      83 11.4    0.879    0.884   22.142   22.172
 make_m2s                          5014 13.6    0.080    0.083   19.976   20.777
 cp_dbcsr_syevd                      83 12.4    0.006    0.006   20.397   20.398
 make_images                       5014 14.6    3.762    3.936   19.494   20.297
 multiply_cannon_metrocomm3       10028 15.6    0.024    0.024   19.195   20.278
 ot_diis_step                       117 11.6    0.022    0.022   20.165   20.166
 apply_preconditioner_dbcsr         128 12.6    0.000    0.000   19.403   19.596
 apply_single                       128 13.6    0.001    0.001   19.403   19.596
 multiply_cannon_multrec          10028 15.6   10.537   12.247   17.943   18.011
 cp_fm_diag_elpa                     83 13.4    0.000    0.000   17.173   17.174
 cp_fm_diag_elpa_base                83 14.4   12.838   14.362   17.169   17.169
 sum_up_and_integrate               128 10.3    0.322    0.323   15.727   15.825
 multiply_cannon_sync_h2d         10028 15.6   15.653   15.667   15.653   15.667
 integrate_v_rspace                 128 11.3    0.004    0.004   15.405   15.505
 qs_rho_update_rho_low              128  7.7    0.001    0.001   15.059   15.073
 calculate_rho_elec                 128  8.7    0.482    0.483   15.059   15.072
 make_images_data                  5014 15.6    0.061    0.065   10.724   12.385
 hybrid_alltoall_any               5200 16.5    1.299    3.031   10.808   12.324
 init_scf_run                        11  5.9    0.000    0.001   11.984   11.985
 scf_env_initial_rho_setup           11  6.9    0.001    0.002   11.984   11.984
 qs_ot_get_derivative_diag           77 12.4    0.002    0.003    9.621    9.650
 cp_fm_cholesky_decompose            22 10.9    9.064    9.123    9.064    9.123
 dbcsr_mm_accdrv_process          20762 16.1    3.712    5.410    7.168    8.996
 wfi_extrapolate                     11  7.9    0.001    0.001    8.740    8.740
 grid_integrate_task_list           128 12.3    8.542    8.739    8.542    8.739
 pw_transfer                       1547 11.6    0.091    0.092    8.489    8.495
 fft_wrap_pw1pw2                   1291 12.7    0.011    0.011    8.254    8.261
 qs_energies_init_hamiltonians       11  5.9    0.001    0.001    7.990    7.991
 fft_wrap_pw1pw2_140                523 13.2    0.540    0.547    7.305    7.319
 mp_alltoall_d11v                  2415 14.1    6.973    7.110    6.973    7.110
 calculate_dm_sparse                128  9.5    0.001    0.001    6.667    6.769
 cp_dbcsr_sm_fm_multiply             37  9.5    0.002    0.002    6.312    6.406
 grid_collocate_task_list           128  9.7    6.337    6.374    6.337    6.374
 fft3d_ps                          1291 14.7    2.770    2.777    6.300    6.319
 copy_dbcsr_to_fm                   186 11.8    0.004    0.004    6.081    6.190
 density_rs2pw                      128  9.7    0.005    0.005    6.114    6.142
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="410", plot="h2o_256_md", label="(8n/1r/12t)", y=289.169000, yerr=0.000000
PlotPoint: name="411", plot="h2o_256_md_mem", label="(8n/1r/12t)", y=2643.272727, yerr=179.475038
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/21/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    23 x    23 x    23      234439235724792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                       234.439236E+12       0.0%      0.0%    100.0%
 flops max/rank                      2.766000E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         9634225188       0.0%      0.0%    100.0%
 number of processed stacks                419739       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0   22952.9
 marketing flops                     1.742116E+15
 -------------------------------------------------------------------------------
 # multiplications                            111
 max memory usage/rank               1.261793E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                  458208
 MPI messages size (bytes):
  total size                         3.456111E+12
  min size                           0.000000E+00
  max size                          18.735064E+06
  average size                       7.542668E+06
 MPI breakdown and total messages size (bytes):
             size <=      128              112896                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                 224                  5687808
     32768 < size <=   131072               10528                813356544
    131072 < size <=  4194304               36422              76284728544
   4194304 < size <= 16777216              294266            3312457683808
  16777216 < size                            3872              66548597808
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 255669.
 MP_Allreduce         3059                   6274.
 MP_Sync                 4
 MP_Alltoall            54                3736884.
 MP_SendRecv           285                  19200.
 MP_ISendRecv          285                  19200.
 MP_Wait              1017
 MP_ISend              642                 197829.
 MP_IRecv              642                 197607.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.052    0.119   85.287   85.309
 qs_energies                          1  2.0    0.000    0.001   84.691   84.715
 ls_scf                               1  3.0    0.002    0.017   83.756   83.769
 dbcsr_multiply_generic             111  6.7    0.015    0.016   72.810   72.968
 multiply_cannon                    111  7.7    0.018    0.021   55.885   57.100
 multiply_cannon_loop               111  8.7    0.209    0.224   52.451   53.833
 ls_scf_main                          1  4.0    0.000    0.003   52.479   52.479
 density_matrix_trs4                  2  5.0    0.002    0.003   47.019   47.110
 ls_scf_init_scf                      1  4.0    0.000    0.001   28.224   28.225
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   27.147   27.201
 mp_waitall_1                     11031 10.9   22.693   25.614   22.693   25.614
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   25.040   25.058
 multiply_cannon_multrec           2664  9.7    8.169    8.901   15.470   17.191
 multiply_cannon_sync_h2d          2664  9.7   13.594   15.510   13.594   15.510
 make_m2s                           222  7.7    0.008    0.011   13.254   13.737
 make_images                        222  8.7    0.099    0.110   13.232   13.717
 multiply_cannon_metrocomm1        2664  9.7    0.009    0.010    9.757   12.701
 multiply_cannon_metrocomm3        2664  9.7    0.009    0.010    5.473    8.876
 make_images_data                   222  9.7    0.004    0.005    7.791    8.343
 hybrid_alltoall_any                227 10.6    0.215    1.843    6.622    8.254
 dbcsr_mm_accdrv_process           4760 10.4    0.508    0.617    6.921    7.874
 dbcsr_mm_accdrv_process_sort      4760 11.4    6.213    7.097    6.213    7.097
 calculate_norms                   4752  9.8    5.514    6.129    5.514    6.129
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.051    5.178
 mp_sum_l                           807  5.4    3.182    4.777    3.182    4.777
 multiply_cannon_metrocomm4        2442  9.7    0.012    0.015    2.055    3.723
 mp_irecv_dv                       6231 10.9    2.038    3.689    2.038    3.689
 make_images_sizes                  222  9.7    0.000    0.000    0.802    3.588
 mp_alltoall_i44                    222 10.7    0.801    3.588    0.801    3.588
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    2.322    3.472
 arnoldi_extremal                     4  6.8    0.000    0.000    3.296    3.325
 arnoldi_normal_ev                    4  7.8    0.001    0.002    3.296    3.325
 build_subspace                      16  8.4    0.009    0.012    3.201    3.203
 ls_scf_post                          1  4.0    0.000    0.001    3.052    3.067
 ls_scf_store_result                  1  5.0    0.000    0.000    2.878    2.915
 dbcsr_special_finalize             555  9.7    0.005    0.006    2.310    2.774
 dbcsr_merge_single_wm              555 10.7    0.457    0.592    2.302    2.766
 make_images_pack                   222  9.7    2.205    2.619    2.207    2.621
 dbcsr_matrix_vector_mult           304  9.0    0.003    0.010    2.372    2.604
 dbcsr_sort_data                    658 11.4    2.103    2.533    2.103    2.533
 dbcsr_matrix_vector_mult_local     304 10.0    2.070    2.458    2.072    2.460
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.204    2.287
 buffer_matrices_ensure_size        222  8.7    1.759    2.071    1.759    2.071
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.732    1.735
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.723    1.725
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.005    1.723    1.725
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="500", plot="h2o_32_nrep3_ls", label="(8n/12r/1t)", y=85.309000, yerr=0.000000
PlotPoint: name="501", plot="h2o_32_nrep3_ls_mem", label="(8n/12r/1t)", y=1142.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/22/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    23 x    23 x    23      234439235724792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                       234.439236E+12       0.0%      0.0%    100.0%
 flops max/rank                      5.588524E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         9634225188       0.0%      0.0%    100.0%
 number of processed stacks                368848       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0   26119.8
 marketing flops                     1.742116E+15
 -------------------------------------------------------------------------------
 # multiplications                            111
 max memory usage/rank               2.102362E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                  106560
 MPI messages size (bytes):
  total size                         2.699093E+12
  min size                           0.000000E+00
  max size                          72.286792E+06
  average size                      25.329324E+06
 MPI breakdown and total messages size (bytes):
             size <=      128               23040                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                3264                325830144
    131072 < size <=  4194304                5280               3328561104
   4194304 < size <= 16777216               12709             156766962056
  16777216 < size                           62267            2538670978840
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 266696.
 MP_Allreduce         3058                  10339.
 MP_Sync                 4
 MP_Alltoall            47               15335933.
 MP_SendRecv           141                  57600.
 MP_ISendRecv          141                  57600.
 MP_Wait               687
 MP_ISend              462                 414589.
 MP_IRecv              462                 413870.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.040    0.108   90.665   90.667
 qs_energies                          1  2.0    0.000    0.000   90.071   90.075
 ls_scf                               1  3.0    0.000    0.000   88.617   88.621
 dbcsr_multiply_generic             111  6.7    0.015    0.015   74.684   75.035
 multiply_cannon                    111  7.7    0.028    0.043   52.960   56.526
 ls_scf_main                          1  4.0    0.000    0.000   54.398   54.408
 multiply_cannon_loop               111  8.7    0.116    0.123   49.663   52.651
 density_matrix_trs4                  2  5.0    0.002    0.003   48.754   48.980
 ls_scf_init_scf                      1  4.0    0.000    0.002   30.689   30.691
 ls_scf_init_matrix_S                 1  5.0    0.000    0.001   29.494   29.593
 mp_waitall_1                      9105 10.9   20.305   29.001   20.305   29.001
 multiply_cannon_multrec           1332  9.7   13.215   17.177   22.437   27.540
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.058   27.070
 multiply_cannon_metrocomm3        1332  9.7    0.006    0.008   11.355   19.979
 make_m2s                           222  7.7    0.006    0.008   14.938   15.596
 make_images                        222  8.7    1.562    1.932   14.908   15.566
 dbcsr_mm_accdrv_process           4041 10.4    0.311    0.454    8.820   10.373
 dbcsr_mm_accdrv_process_sort      4041 11.4    8.411    9.918    8.411    9.918
 make_images_data                   222  9.7    0.004    0.004    8.362    9.331
 hybrid_alltoall_any                227 10.6    0.523    2.441    7.795    8.688
 mp_sum_l                           807  5.4    5.505    8.680    5.505    8.680
 multiply_cannon_metrocomm4        1221  9.7    0.006    0.008    3.244    7.707
 mp_irecv_dv                       3311 11.0    3.223    7.642    3.223    7.642
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    4.213    6.831
 calculate_norms                   2376  9.8    6.022    6.718    6.022    6.718
 multiply_cannon_sync_h2d          1332  9.7    4.820    6.011    4.820    6.011
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.072    5.290
 arnoldi_extremal                     4  6.8    0.000    0.000    4.696    4.721
 arnoldi_normal_ev                    4  7.8    0.001    0.005    4.696    4.721
 build_subspace                      16  8.4    0.014    0.021    4.440    4.442
 ls_scf_post                          1  4.0    0.000    0.000    3.529    3.534
 dbcsr_matrix_vector_mult           304  9.0    0.005    0.017    3.164    3.405
 ls_scf_store_result                  1  5.0    0.000    0.000    3.242    3.354
 dbcsr_matrix_vector_mult_local     304 10.0    2.736    3.214    2.738    3.216
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.004    1.214    3.026
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    2.497    2.592
 make_images_pack                   222  9.7    2.020    2.419    2.022    2.421
 mp_allgather_i34                   111  8.7    0.992    2.162    0.992    2.162
 dbcsr_sort_data                    436 11.2    1.833    2.024    1.833    2.024
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.860    1.862
 dbcsr_data_new                    4174 10.1    1.620    1.858    1.620    1.858
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.847    1.850
 qs_ks_build_kohn_sham_matrix         3  8.3    0.001    0.009    1.847    1.850
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="502", plot="h2o_32_nrep3_ls", label="(8n/6r/2t)", y=90.667000, yerr=0.000000
PlotPoint: name="503", plot="h2o_32_nrep3_ls_mem", label="(8n/6r/2t)", y=1748.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/23/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    23 x    23 x    23      234439235724792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                       234.439236E+12       0.0%      0.0%    100.0%
 flops max/rank                      8.404608E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         9634225188       0.0%      0.0%    100.0%
 number of processed stacks                353133       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0   27282.1
 marketing flops                     1.742118E+15
 -------------------------------------------------------------------------------
 # multiplications                            111
 max memory usage/rank               2.703647E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                   46176
 MPI messages size (bytes):
  total size                         1.924064E+12
  min size                           0.000000E+00
  max size                         108.059888E+06
  average size                      41.668048E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                9984                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304                3328               1170063360
   4194304 < size <= 16777216                1870              19378539600
  16777216 < size                           30994            1903514987232
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 265470.
 MP_Allreduce         3058                  11181.
 MP_Sync                 4
 MP_Alltoall            47               23526250.
 MP_SendRecv            93                  57600.
 MP_ISendRecv           93                  57600.
 MP_Wait               639
 MP_ISend              462                 560046.
 MP_IRecv              462                 560662.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.050    0.091   94.251   94.252
 qs_energies                          1  2.0    0.002    0.014   93.563   93.595
 ls_scf                               1  3.0    0.003    0.021   92.165   92.185
 dbcsr_multiply_generic             111  6.7    0.015    0.016   76.634   76.940
 ls_scf_main                          1  4.0    0.000    0.002   57.447   57.456
 multiply_cannon                    111  7.7    0.040    0.100   53.038   56.485
 multiply_cannon_loop               111  8.7    0.100    0.106   49.338   53.121
 density_matrix_trs4                  2  5.0    0.002    0.012   51.605   51.769
 mp_waitall_1                      7281 11.0   23.843   34.288   23.843   34.288
 ls_scf_init_scf                      1  4.0    0.000    0.002   31.092   31.105
 ls_scf_init_matrix_S                 1  5.0    0.000    0.001   29.544   29.623
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.115   27.131
 multiply_cannon_multrec            888  9.7   12.661   15.110   21.180   24.201
 multiply_cannon_metrocomm3         888  9.7    0.004    0.004   10.969   23.405
 make_m2s                           222  7.7    0.006    0.006   16.875   18.239
 make_images                        222  8.7    1.969    2.288   16.836   18.199
 hybrid_alltoall_any                227 10.6    0.622    2.872    9.346   10.681
 make_images_data                   222  9.7    0.003    0.004    9.645   10.680
 dbcsr_mm_accdrv_process           3754 10.4    0.238    0.427    8.052    9.246
 mp_sum_l                           807  5.4    5.204    9.220    5.204    9.220
 dbcsr_mm_accdrv_process_sort      3754 11.4    7.679    8.819    7.679    8.819
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    4.059    7.538
 multiply_cannon_sync_h2d           888  9.7    6.044    7.294    6.044    7.294
 multiply_cannon_metrocomm4         777  9.7    0.004    0.005    2.394    6.733
 mp_irecv_dv                       2335 11.1    2.379    6.678    2.379    6.678
 multiply_cannon_metrocomm1         888  9.7    0.003    0.003    3.856    6.623
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.902    5.156
 arnoldi_extremal                     4  6.8    0.000    0.000    5.027    5.050
 arnoldi_normal_ev                    4  7.8    0.001    0.004    5.027    5.049
 build_subspace                      16  8.4    0.014    0.020    4.722    4.729
 calculate_norms                   1584  9.8    4.268    4.629    4.268    4.629
 mp_allgather_i34                   111  8.7    1.526    3.886    1.526    3.886
 dbcsr_matrix_vector_mult           304  9.0    0.005    0.017    3.414    3.742
 ls_scf_post                          1  4.0    0.003    0.021    3.624    3.647
 dbcsr_matrix_vector_mult_local     304 10.0    3.014    3.585    3.016    3.587
 ls_scf_store_result                  1  5.0    0.000    0.000    3.326    3.438
 ls_scf_dm_to_ks                      2  5.0    0.000    0.001    2.715    2.802
 make_images_pack                   222  9.7    1.815    2.141    1.818    2.144
 dbcsr_sort_data                    325 11.1    1.894    2.043    1.894    2.043
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    1.996    2.010
 dbcsr_data_release                9322 10.9    1.295    2.000    1.295    2.000
 rebuild_ks_matrix                    3  7.3    0.000    0.000    1.978    1.992
 qs_ks_build_kohn_sham_matrix         3  8.3    0.002    0.017    1.978    1.992
 make_images_sizes                  222  9.7    0.000    0.000    0.893    1.977
 mp_alltoall_i44                    222 10.7    0.893    1.977    0.893    1.977
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="504", plot="h2o_32_nrep3_ls", label="(8n/4r/3t)", y=94.252000, yerr=0.000000
PlotPoint: name="505", plot="h2o_32_nrep3_ls_mem", label="(8n/4r/3t)", y=2198.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/24/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    23 x    23 x    23      234439235724792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                       234.439236E+12       0.0%      0.0%    100.0%
 flops max/rank                     10.747127E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         9634225188       0.0%      0.0%    100.0%
 number of processed stacks                369794       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0   26053.0
 marketing flops                     1.742116E+15
 -------------------------------------------------------------------------------
 # multiplications                            111
 max memory usage/rank               3.320418E+09
 # max total images/rank                        3
 # max 3D layers                                1
 # MPI messages exchanged                   50616
 MPI messages size (bytes):
  total size                         1.536549E+12
  min size                           0.000000E+00
  max size                          72.286792E+06
  average size                      30.356986E+06
 MPI breakdown and total messages size (bytes):
             size <=      128               10368                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                1056                104411904
    131072 < size <=  4194304                3168                831638784
   4194304 < size <= 16777216                3103              33613273640
  16777216 < size                           32921            1501999894888
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 266696.
 MP_Allreduce         3058                  13371.
 MP_Sync                 4
 MP_Alltoall            47               30278988.
 MP_SendRecv            69                  86400.
 MP_ISendRecv           69                  86400.
 MP_Wait               531
 MP_ISend              378                 823502.
 MP_IRecv              378                 823753.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.109    0.169   96.913   96.915
 qs_energies                          1  2.0    0.000    0.000   95.944   95.958
 ls_scf                               1  3.0    0.000    0.001   94.271   94.285
 dbcsr_multiply_generic             111  6.7    0.017    0.018   78.184   78.457
 ls_scf_main                          1  4.0    0.000    0.000   58.457   58.458
 multiply_cannon                    111  7.7    0.053    0.101   51.485   56.423
 density_matrix_trs4                  2  5.0    0.002    0.003   52.473   52.621
 multiply_cannon_loop               111  8.7    0.115    0.126   46.349   49.371
 ls_scf_init_scf                      1  4.0    0.000    0.002   32.561   32.563
 ls_scf_init_matrix_S                 1  5.0    0.000    0.002   31.415   31.486
 mp_waitall_1                      6369 11.0   22.548   29.911   22.548   29.911
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   28.909   28.922
 multiply_cannon_multrec           1332  9.7   14.228   17.526   22.080   25.575
 make_m2s                           222  7.7    0.007    0.008   21.064   22.550
 make_images                        222  8.7    3.126    3.595   21.013   22.503
 multiply_cannon_metrocomm3        1332  9.7    0.003    0.004    9.218   16.937
 make_images_data                   222  9.7    0.004    0.004   11.810   13.414
 hybrid_alltoall_any                227 10.6    0.800    3.842   11.061   13.241
 dbcsr_mm_accdrv_process           3641 10.4    0.231    0.425    7.492    9.009
 dbcsr_mm_accdrv_process_sort      3641 11.4    7.114    8.590    7.114    8.590
 mp_sum_l                           807  5.4    4.065    7.565    4.065    7.565
 multiply_cannon_sync_h2d          1332  9.7    5.488    6.143    5.488    6.143
 multiply_cannon_metrocomm4        1110  9.7    0.004    0.006    2.082    5.997
 mp_irecv_dv                       3229 10.9    2.059    5.925    2.059    5.925
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    3.137    5.877
 arnoldi_extremal                     4  6.8    0.000    0.000    5.219    5.232
 arnoldi_normal_ev                    4  7.8    0.001    0.005    5.219    5.232
 build_subspace                      16  8.4    0.014    0.021    4.883    4.891
 mp_allgather_i34                   111  8.7    2.264    4.770    2.264    4.770
 multiply_cannon_metrocomm1        1332  9.7    0.003    0.003    2.351    4.762
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.510    4.668
 calculate_norms                   2376  9.8    4.194    4.503    4.194    4.503
 dbcsr_matrix_vector_mult           304  9.0    0.006    0.016    3.563    3.859
 dbcsr_matrix_vector_mult_local     304 10.0    3.182    3.681    3.184    3.683
 dbcsr_sort_data                    658 11.4    3.041    3.421    3.041    3.421
 ls_scf_post                          1  4.0    0.006    0.016    3.253    3.267
 dbcsr_special_finalize             555  9.7    0.006    0.006    2.781    3.260
 dbcsr_merge_single_wm              555 10.7    0.529    0.656    2.773    3.252
 ls_scf_store_result                  1  5.0    0.000    0.000    2.974    3.049
 ls_scf_dm_to_ks                      2  5.0    0.000    0.006    2.894    2.954
 dbcsr_data_release               10477 10.7    1.572    2.392    1.572    2.392
 dbcsr_finalize                     304  7.8    0.049    0.061    1.793    1.979
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="506", plot="h2o_32_nrep3_ls", label="(8n/3r/4t)", y=96.915000, yerr=0.000000
PlotPoint: name="507", plot="h2o_32_nrep3_ls_mem", label="(8n/3r/4t)", y=2724.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/25/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    23 x    23 x    23      234439235724792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                       234.439236E+12       0.0%      0.0%    100.0%
 flops max/rank                     15.383312E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         9634225188       0.0%      0.0%    100.0%
 number of processed stacks                336818       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0   28603.7
 marketing flops                     1.742118E+15
 -------------------------------------------------------------------------------
 # multiplications                            111
 max memory usage/rank               4.624925E+09
 # max total images/rank                        1
 # max 3D layers                                1
 # MPI messages exchanged                   10656
 MPI messages size (bytes):
  total size                         1.149035E+12
  min size                           0.000000E+00
  max size                         203.538048E+06
  average size                     107.829832E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                2304                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304                 768                702038016
   4194304 < size <= 16777216                   0                        0
  16777216 < size                            7584            1148332810224
 -------------------------------------------------------------------------------
 -                                                                             -
 -                      DBCSR MESSAGE PASSING PERFORMANCE                      -
 -                                                                             -
 -------------------------------------------------------------------------------
 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Bcast                2                     12.
 MP_Allreduce          705                    128.
 MP_Alltoall           310               12920694.
 MP_ISend             1776               40180424.
 MP_IRecv             1776               40465030.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 265558.
 MP_Allreduce         3049                  15663.
 MP_Sync                 4
 MP_Alltoall            47               46208988.
 MP_SendRecv            45                 115200.
 MP_ISendRecv           45                 115200.
 MP_Wait               528
 MP_ISend              420                 924980.
 MP_IRecv              420                 924528.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.054    0.089   98.766   98.786
 qs_energies                          1  2.0    0.000    0.000   97.959   97.966
 ls_scf                               1  3.0    0.000    0.000   96.041   96.047
 dbcsr_multiply_generic             111  6.7    0.017    0.018   77.698   77.852
 ls_scf_main                          1  4.0    0.000    0.000   61.791   61.791
 multiply_cannon                    111  7.7    0.067    0.137   54.990   60.160
 density_matrix_trs4                  2  5.0    0.002    0.002   54.817   54.898
 multiply_cannon_loop               111  8.7    0.069    0.079   50.444   51.913
 mp_waitall_1                      5436 11.0   26.482   32.215   26.482   32.215
 ls_scf_init_scf                      1  4.0    0.000    0.000   30.655   30.658
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   29.467   29.509
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   27.300   27.308
 multiply_cannon_multrec            444  9.7   13.948   16.586   20.972   24.658
 make_m2s                           222  7.7    0.005    0.005   17.838   20.340
 make_images                        222  8.7    3.715    4.412   17.776   20.279
 multiply_cannon_metrocomm1         444  9.7    0.002    0.002   11.068   15.980
 multiply_cannon_metrocomm3         444  9.7    0.001    0.001    6.077   14.806
 make_images_data                   222  9.7    0.003    0.004   10.138   12.479
 hybrid_alltoall_any                227 10.6    0.789    3.771    9.829   12.364
 multiply_cannon_sync_h2d           444  9.7    6.494    8.828    6.494    8.828
 dbcsr_mm_accdrv_process           3003 10.4    0.180    0.366    6.733    7.860
 dbcsr_mm_accdrv_process_sort      3003 11.4    6.408    7.497    6.408    7.497
 mp_allgather_i34                   111  8.7    2.785    7.004    2.785    7.004
 arnoldi_extremal                     4  6.8    0.000    0.000    5.913    5.919
 arnoldi_normal_ev                    4  7.8    0.001    0.005    5.913    5.919
 mp_sum_l                           807  5.4    2.901    5.689    2.901    5.689
 build_subspace                      16  8.4    0.015    0.019    5.531    5.540
 apply_matrix_preconditioner          6  5.3    0.000    0.000    4.566    4.706
 dbcsr_matrix_vector_mult           304  9.0    0.007    0.017    4.202    4.440
 dbcsr_multiply_generic_mpsum_f      86  7.8    0.000    0.000    2.019    4.362
 dbcsr_matrix_vector_mult_local     304 10.0    3.694    4.157    3.696    4.159
 multiply_cannon_metrocomm4         333  9.7    0.001    0.002    1.634    4.110
 mp_irecv_dv                       1241 11.2    1.614    4.089    1.614    4.089
 calculate_norms                    792  9.8    3.548    3.693    3.548    3.693
 ls_scf_post                          1  4.0    0.000    0.000    3.594    3.601
 make_images_sizes                  222  9.7    0.000    0.000    1.051    3.551
 mp_alltoall_i44                    222 10.7    1.051    3.551    1.051    3.551
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    3.393    3.478
 ls_scf_store_result                  1  5.0    0.000    0.000    3.382    3.417
 dbcsr_finalize                     304  7.8    0.062    0.078    2.211    2.318
 dbcsr_merge_all                    275  8.9    0.476    0.528    2.060    2.152
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="508", plot="h2o_32_nrep3_ls", label="(8n/2r/6t)", y=98.786000, yerr=0.000000
PlotPoint: name="509", plot="h2o_32_nrep3_ls_mem", label="(8n/2r/6t)", y=3627.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


 ~~~~~~~~~ RESULT ~~~~~~~~~
RESULT file: /scratch/snx3000/mkrack/rt/../rt/CRAY-XC50-gnu/0f4c3be663d366d31f5e87b3e15a929b1755fd76_performance_tests/26/result.log


 @@@@@@@@@@ Run number: 1 @@@@@@@@@@

 -------------------------------------------------------------------------------
 -                                                                             -
 -                                DBCSR STATISTICS                             -
 -                                                                             -
 -------------------------------------------------------------------------------
 COUNTER                                    TOTAL       BLAS       SMM       ACC
 flops    23 x    23 x    23      234439235724792       0.0%      0.0%    100.0%
 flops inhomo. stacks                           0       0.0%      0.0%      0.0%
 flops total                       234.439236E+12       0.0%      0.0%    100.0%
 flops max/rank                     30.358840E+12       0.0%      0.0%    100.0%
 matmuls inhomo. stacks                         0       0.0%      0.0%      0.0%
 matmuls total                         9634225188       0.0%      0.0%    100.0%
 number of processed stacks                339931       0.0%      0.0%    100.0%
 average stack size                                     0.0       0.0   28341.7
 marketing flops                     1.742118E+15
 -------------------------------------------------------------------------------
 # multiplications                            111
 max memory usage/rank               8.886833E+09
 # max total images/rank                        2
 # max 3D layers                                1
 # MPI messages exchanged                    4440
 MPI messages size (bytes):
  total size                       770.525954E+09
  min size                           0.000000E+00
  max size                         399.069120E+06
  average size                     173.541888E+06
 MPI breakdown and total messages size (bytes):
             size <=      128                 640                        0
       128 < size <=     8192                   0                        0
      8192 < size <=    32768                   0                        0
     32768 < size <=   131072                   0                        0
    131072 < size <=  4194304                 640                468025344
   4194304 < size <= 16777216                   0                        0
  16777216 < size                            3160             770057961712
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                         MESSAGE PASSING PERFORMANCE                         -
 -                                                                             -
 -------------------------------------------------------------------------------

 ROUTINE             CALLS      AVE VOLUME [Bytes]
 MP_Group                4
 MP_Bcast             1026                 284111.
 MP_Allreduce         3043                  21950.
 MP_Sync                 4
 MP_Alltoall            47               88727262.
 MP_SendRecv            42                 732600.
 MP_ISendRecv           42                 732600.
 MP_Wait               267
 MP_ISend              180                3337386.
 MP_IRecv              180                3339494.
 -------------------------------------------------------------------------------
 -------------------------------------------------------------------------------
 -                                                                             -
 -                                T I M I N G                                  -
 -                                                                             -
 -------------------------------------------------------------------------------
 SUBROUTINE                       CALLS  ASD         SELF TIME        TOTAL TIME
                                MAXIMUM       AVERAGE  MAXIMUM  AVERAGE  MAXIMUM
 CP2K                                 1  1.0    0.168    0.186  107.716  107.717
 qs_energies                          1  2.0    0.000    0.000  106.108  106.123
 ls_scf                               1  3.0    0.000    0.000  103.247  103.262
 dbcsr_multiply_generic             111  6.7    0.024    0.027   77.418   77.553
 ls_scf_main                          1  4.0    0.000    0.000   65.773   65.774
 density_matrix_trs4                  2  5.0    0.002    0.003   56.918   56.993
 multiply_cannon                    111  7.7    0.198    0.300   49.474   50.481
 multiply_cannon_loop               111  8.7    0.067    0.069   46.127   47.873
 ls_scf_init_scf                      1  4.0    0.000    0.000   33.821   33.821
 ls_scf_init_matrix_S                 1  5.0    0.000    0.000   32.494   32.516
 matrix_sqrt_Newton_Schulz            2  6.5    0.001    0.001   29.695   29.706
 mp_waitall_1                      4527 11.1   21.953   26.039   21.953   26.039
 make_m2s                           222  7.7    0.005    0.005   23.849   24.719
 make_images                        222  8.7    4.573    4.976   23.743   24.612
 multiply_cannon_multrec            444  9.7   17.826   18.430   22.416   23.000
 hybrid_alltoall_any                227 10.6    1.663    3.640   12.924   15.462
 make_images_data                   222  9.7    0.003    0.003   13.109   15.413
 multiply_cannon_metrocomm3         444  9.7    0.001    0.001   10.270   11.513
 multiply_cannon_sync_h2d           444  9.7    8.844    8.880    8.844    8.880
 arnoldi_extremal                     4  6.8    0.000    0.000    7.439    7.452
 arnoldi_normal_ev                    4  7.8    0.002    0.008    7.439    7.452
 build_subspace                      16  8.4    0.026    0.037    6.892    6.901
 dbcsr_matrix_vector_mult           304  9.0    0.009    0.025    5.547    5.675
 dbcsr_matrix_vector_mult_local     304 10.0    5.041    5.353    5.043    5.356
 apply_matrix_preconditioner          6  5.3    0.000    0.000    5.057    5.313
 ls_scf_dm_to_ks                      2  5.0    0.000    0.000    4.764    4.852
 dbcsr_mm_accdrv_process           1814 10.4    0.186    0.325    4.420    4.542
 dbcsr_mm_accdrv_process_sort      1814 11.4    4.116    4.244    4.116    4.244
 ls_scf_post                          1  4.0    0.000    0.000    3.654    3.668
 make_images_sizes                  222  9.7    0.000    0.000    1.426    3.440
 mp_alltoall_i44                    222 10.7    1.426    3.440    1.426    3.440
 ls_scf_store_result                  1  5.0    0.000    0.000    3.399    3.419
 calculate_norms                    792  9.8    3.243    3.272    3.243    3.272
 dbcsr_finalize                     304  7.8    0.082    0.089    3.066    3.109
 mp_allgather_i34                   111  8.7    0.996    3.085    0.996    3.085
 mp_sum_l                           807  5.4    1.787    3.013    1.787    3.013
 dbcsr_merge_all                    275  8.9    0.889    0.914    2.851    2.886
 dbcsr_data_release               12724 10.6    2.326    2.871    2.326    2.871
 dbcsr_complete_redistribute          5  7.6    1.439    1.469    2.752    2.838
 qs_energies_init_hamiltonians        1  3.0    0.000    0.001    2.831    2.831
 matrix_ls_to_qs                      2  6.0    0.000    0.000    2.392    2.496
 dbcsr_sort_data                    325 11.1    2.441    2.483    2.441    2.483
 dbcsr_new_transposed                 4  7.5    0.243    0.253    2.284    2.296
 dbcsr_frobenius_norm                74  6.6    2.056    2.135    2.201    2.250
 dbcsr_add_d                        103  6.2    0.000    0.000    2.132    2.201
 dbcsr_add_anytype                  103  7.2    0.860    0.892    2.132    2.201
 qs_ks_update_qs_env                  3  6.3    0.000    0.000    2.193    2.194
 -------------------------------------------------------------------------------
 ~ ~ ~ ~  DATA POINTS  ~ ~ ~ ~
PlotPoint: name="510", plot="h2o_32_nrep3_ls", label="(8n/1r/12t)", y=107.717000, yerr=0.000000
PlotPoint: name="511", plot="h2o_32_nrep3_ls_mem", label="(8n/1r/12t)", y=6857.000000, yerr=0.000000
 ~ ~ ~ ~ END DATA POINTS ~ ~ ~
 ~~~~~~ END RESULT ~~~~~~~~


========= END RESULTS ===========

CommitSHA: 0f4c3be663d366d31f5e87b3e15a929b1755fd76
Summary: empty
Status: OK